diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..a5c8b59c6725f43b68dfdefd11d85ec5be901fc2
--- /dev/null
+++ b/README.md
@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+base_model: openai/whisper-large-v3
+tags:
+- generated_from_trainer
+datasets:
+- mozilla-foundation/common_voice_16_0
+metrics:
+- wer
+model-index:
+- name: whisper-large-v3-pt-cv16-cuda
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: mozilla-foundation/common_voice_16_0 pt
+      type: mozilla-foundation/common_voice_16_0
+      split: None
+      args: pt
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.9998545572074984
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# whisper-large-v3-pt-cv16-cuda
+
+This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co./openai/whisper-large-v3) on the mozilla-foundation/common_voice_16_0 pt dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1325
+- Wer: 0.9999
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2000
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.199         | 0.26  | 1000 | 0.1563          | 0.1124 |
+| 0.1654        | 0.52  | 2000 | 0.1500          | 0.1052 |
+| 0.1794        | 0.77  | 3000 | 0.1379          | 0.0997 |
+| 0.0821        | 1.03  | 4000 | 0.1321          | 1.0007 |
+| 0.1292        | 1.29  | 5000 | 0.1325          | 0.9999 |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.2.0.dev20231212
+- Datasets 2.15.1.dev0
+- Tokenizers 0.15.0
diff --git a/all_results.json b/all_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..42ef0f53a894a4194b11a1231b28963705a03296
--- /dev/null
+++ b/all_results.json
@@ -0,0 +1,14 @@
+{
+    "epoch": 1.29,
+    "eval_loss": 0.132488414645195,
+    "eval_runtime": 171706.1904,
+    "eval_samples": 9399,
+    "eval_samples_per_second": 0.055,
+    "eval_steps_per_second": 0.007,
+    "eval_wer": 0.9998545572074984,
+    "train_loss": 0.05041759390830994,
+    "train_runtime": 1177508.0135,
+    "train_samples": 30998,
+    "train_samples_per_second": 0.034,
+    "train_steps_per_second": 0.004
+}
\ No newline at end of file
diff --git a/checkpoint-1000/config.json b/checkpoint-1000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..caa8aea5ccb9a4c479137c1f0ded8dc3bcc33fb2
--- /dev/null
+++ b/checkpoint-1000/config.json
@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "openai/whisper-large-v3",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": true,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}
diff --git a/checkpoint-1000/generation_config.json b/checkpoint-1000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c184c23d34e10a8eb965f82773d9f8e3fb90c3d
--- /dev/null
+++ b/checkpoint-1000/generation_config.json
@@ -0,0 +1,264 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50360
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 1,
+  "max_length": 448,
+  "no_timestamps_token_id": 50364,
+  "pad_token_id": 50257,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.37.0.dev0"
+}
diff --git a/checkpoint-1000/model-00001-of-00002.safetensors b/checkpoint-1000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6f1025125506fdcc58ff101ababbac69b371201c
--- /dev/null
+++ b/checkpoint-1000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14da2025731d949006200c34abfb6aa1be4cc2350ecc27dc6af559603a86225d
+size 4993448880
diff --git a/checkpoint-1000/model-00002-of-00002.safetensors b/checkpoint-1000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..10a0d133fd78ff736134d4d4cf30dca68ec72d31
--- /dev/null
+++ b/checkpoint-1000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b38b2d250388274dbab6a134b7ff4184cb3525599666efa7cdefed5c99d82c
+size 1180663192
diff --git a/checkpoint-1000/model.safetensors.index.json b/checkpoint-1000/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..c40d652c9b765dc6b1f8a90b16063b93b7b5c888
--- /dev/null
+++ b/checkpoint-1000/model.safetensors.index.json
@@ -0,0 +1,1266 @@
+{
+  "metadata": {
+    "total_size": 6173962240
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors"
+  }
+}
diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9997607899730f99dd1ef7ec9b950fc3c19cdd63
--- /dev/null
+++ b/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b7a6a42c8f342e4252296a6744e5aeb820e8d8de08a16c9dd10adc396c1293
+size 12333660476
diff --git a/checkpoint-1000/preprocessor_config.json b/checkpoint-1000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f
--- /dev/null
+++ b/checkpoint-1000/preprocessor_config.json
@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8940433795a5e23f0ce4ca87e4337e0b68d79357
Binary files /dev/null and b/checkpoint-1000/rng_state.pth differ
diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f8d557372e926d2c1d85614b29b7cfb8ea164a52
Binary files /dev/null and b/checkpoint-1000/scheduler.pt differ
diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..689fe6fb372c552c3a3fd474137472ba215ab427
--- /dev/null
+++ b/checkpoint-1000/trainer_state.json
@@ -0,0 +1,270 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25806451612903225,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1499999999999999e-08,
+      "loss": 0.7822,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-08,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6499999999999996e-08,
+      "loss": 0.7809,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9e-08,
+      "loss": 1.2916,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.15e-08,
+      "loss": 0.7645,
+      "step": 125
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.399999999999999e-08,
+      "loss": 1.3379,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.649999999999999e-08,
+      "loss": 0.7722,
+      "step": 175
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.9e-08,
+      "loss": 1.281,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.115e-07,
+      "loss": 0.6998,
+      "step": 225
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.24e-07,
+      "loss": 1.1532,
+      "step": 250
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.365e-07,
+      "loss": 0.583,
+      "step": 275
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.49e-07,
+      "loss": 0.6693,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.615e-07,
+      "loss": 0.3395,
+      "step": 325
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7399999999999997e-07,
+      "loss": 0.3597,
+      "step": 350
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.8649999999999998e-07,
+      "loss": 0.22,
+      "step": 375
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.99e-07,
+      "loss": 0.3449,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.1149999999999998e-07,
+      "loss": 0.2123,
+      "step": 425
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.24e-07,
+      "loss": 0.3362,
+      "step": 450
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.3649999999999998e-07,
+      "loss": 0.175,
+      "step": 475
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.4899999999999997e-07,
+      "loss": 0.3051,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.615e-07,
+      "loss": 0.176,
+      "step": 525
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.74e-07,
+      "loss": 0.2517,
+      "step": 550
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.865e-07,
+      "loss": 0.1863,
+      "step": 575
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9899999999999996e-07,
+      "loss": 0.2614,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.115e-07,
+      "loss": 0.1942,
+      "step": 625
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.24e-07,
+      "loss": 0.2901,
+      "step": 650
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.3650000000000003e-07,
+      "loss": 0.1587,
+      "step": 675
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.4899999999999996e-07,
+      "loss": 0.2128,
+      "step": 700
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.6149999999999995e-07,
+      "loss": 0.1647,
+      "step": 725
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.74e-07,
+      "loss": 0.2473,
+      "step": 750
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.8649999999999997e-07,
+      "loss": 0.1415,
+      "step": 775
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.99e-07,
+      "loss": 0.2367,
+      "step": 800
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.1149999999999995e-07,
+      "loss": 0.1498,
+      "step": 825
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.24e-07,
+      "loss": 0.2161,
+      "step": 850
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.3649999999999997e-07,
+      "loss": 0.144,
+      "step": 875
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.49e-07,
+      "loss": 0.2316,
+      "step": 900
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.615e-07,
+      "loss": 0.1449,
+      "step": 925
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.7399999999999993e-07,
+      "loss": 0.1513,
+      "step": 950
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.864999999999999e-07,
+      "loss": 0.1855,
+      "step": 975
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.99e-07,
+      "loss": 0.199,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.15628743171691895,
+      "eval_runtime": 184706.1006,
+      "eval_samples_per_second": 0.051,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.1124272786037492,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 2.717998645248e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f9b2ac6d109ba135c37e8de1802d3dfa05ab0bb5
Binary files /dev/null and b/checkpoint-1000/training_args.bin differ
diff --git a/checkpoint-2000/config.json b/checkpoint-2000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..caa8aea5ccb9a4c479137c1f0ded8dc3bcc33fb2
--- /dev/null
+++ b/checkpoint-2000/config.json
@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "openai/whisper-large-v3",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": true,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}
diff --git a/checkpoint-2000/generation_config.json b/checkpoint-2000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c184c23d34e10a8eb965f82773d9f8e3fb90c3d
--- /dev/null
+++ b/checkpoint-2000/generation_config.json
@@ -0,0 +1,264 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50360
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 1,
+  "max_length": 448,
+  "no_timestamps_token_id": 50364,
+  "pad_token_id": 50257,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.37.0.dev0"
+}
diff --git a/checkpoint-2000/model-00001-of-00002.safetensors b/checkpoint-2000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..17fb190db90ea05d2df7e15bab0cf3faf754d851
--- /dev/null
+++ b/checkpoint-2000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156e0fd71ba8d6d1a308460a813997db7d653c1f820bd2d5995abd49692f14a1
+size 4993448880
diff --git a/checkpoint-2000/model-00002-of-00002.safetensors b/checkpoint-2000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fd685f435cd6bee482fee41a667379273cc0b05a
--- /dev/null
+++ b/checkpoint-2000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05a1c27b9a9a440db979127057f5f66ec41e211bf68bb2ea3a227c4403c8e60
+size 1180663192
diff --git a/checkpoint-2000/model.safetensors.index.json b/checkpoint-2000/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..c40d652c9b765dc6b1f8a90b16063b93b7b5c888
--- /dev/null
+++ b/checkpoint-2000/model.safetensors.index.json
@@ -0,0 +1,1266 @@
+{
+  "metadata": {
+    "total_size": 6173962240
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors"
+  }
+}
diff --git a/checkpoint-2000/optimizer.pt b/checkpoint-2000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e12119b1b344c128dceffdcbca9a9193f17313cc
--- /dev/null
+++ b/checkpoint-2000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da10ec2e0bf47d4b44db41bb1bfc93e007a4873e0e2ff5dbc5e667cb0168b4f
+size 12333660476
diff --git a/checkpoint-2000/preprocessor_config.json b/checkpoint-2000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f
--- /dev/null
+++ b/checkpoint-2000/preprocessor_config.json
@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-2000/rng_state.pth b/checkpoint-2000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5266f1a0df1c07e66dd192a65c9b980c129eb5b6
Binary files /dev/null and b/checkpoint-2000/rng_state.pth differ
diff --git a/checkpoint-2000/scheduler.pt b/checkpoint-2000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..127cc9accc96cfc23129e9ada9fc59603f1a4317
Binary files /dev/null and b/checkpoint-2000/scheduler.pt differ
diff --git a/checkpoint-2000/trainer_state.json b/checkpoint-2000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e63d36c8f0ba38dac710e86fade92efe8d890bb9
--- /dev/null
+++ b/checkpoint-2000/trainer_state.json
@@ -0,0 +1,519 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5161290322580645,
+  "eval_steps": 1000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1499999999999999e-08,
+      "loss": 0.7822,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-08,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6499999999999996e-08,
+      "loss": 0.7809,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9e-08,
+      "loss": 1.2916,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.15e-08,
+      "loss": 0.7645,
+      "step": 125
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.399999999999999e-08,
+      "loss": 1.3379,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.649999999999999e-08,
+      "loss": 0.7722,
+      "step": 175
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.9e-08,
+      "loss": 1.281,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.115e-07,
+      "loss": 0.6998,
+      "step": 225
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.24e-07,
+      "loss": 1.1532,
+      "step": 250
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.365e-07,
+      "loss": 0.583,
+      "step": 275
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.49e-07,
+      "loss": 0.6693,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.615e-07,
+      "loss": 0.3395,
+      "step": 325
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7399999999999997e-07,
+      "loss": 0.3597,
+      "step": 350
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.8649999999999998e-07,
+      "loss": 0.22,
+      "step": 375
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.99e-07,
+      "loss": 0.3449,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.1149999999999998e-07,
+      "loss": 0.2123,
+      "step": 425
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.24e-07,
+      "loss": 0.3362,
+      "step": 450
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.3649999999999998e-07,
+      "loss": 0.175,
+      "step": 475
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.4899999999999997e-07,
+      "loss": 0.3051,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.615e-07,
+      "loss": 0.176,
+      "step": 525
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.74e-07,
+      "loss": 0.2517,
+      "step": 550
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.865e-07,
+      "loss": 0.1863,
+      "step": 575
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9899999999999996e-07,
+      "loss": 0.2614,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.115e-07,
+      "loss": 0.1942,
+      "step": 625
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.24e-07,
+      "loss": 0.2901,
+      "step": 650
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.3650000000000003e-07,
+      "loss": 0.1587,
+      "step": 675
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.4899999999999996e-07,
+      "loss": 0.2128,
+      "step": 700
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.6149999999999995e-07,
+      "loss": 0.1647,
+      "step": 725
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.74e-07,
+      "loss": 0.2473,
+      "step": 750
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.8649999999999997e-07,
+      "loss": 0.1415,
+      "step": 775
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.99e-07,
+      "loss": 0.2367,
+      "step": 800
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.1149999999999995e-07,
+      "loss": 0.1498,
+      "step": 825
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.24e-07,
+      "loss": 0.2161,
+      "step": 850
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.3649999999999997e-07,
+      "loss": 0.144,
+      "step": 875
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.49e-07,
+      "loss": 0.2316,
+      "step": 900
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.615e-07,
+      "loss": 0.1449,
+      "step": 925
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.7399999999999993e-07,
+      "loss": 0.1513,
+      "step": 950
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.864999999999999e-07,
+      "loss": 0.1855,
+      "step": 975
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.99e-07,
+      "loss": 0.199,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.15628743171691895,
+      "eval_runtime": 184706.1006,
+      "eval_samples_per_second": 0.051,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.1124272786037492,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5.114999999999999e-07,
+      "loss": 0.1301,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 5.24e-07,
+      "loss": 0.2193,
+      "step": 1050
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.365e-07,
+      "loss": 0.1552,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.490000000000001e-07,
+      "loss": 0.1865,
+      "step": 1100
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 5.614999999999999e-07,
+      "loss": 0.1618,
+      "step": 1125
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.739999999999999e-07,
+      "loss": 0.2259,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.865e-07,
+      "loss": 0.1418,
+      "step": 1175
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5.989999999999999e-07,
+      "loss": 0.1916,
+      "step": 1200
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.115e-07,
+      "loss": 0.1295,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.24e-07,
+      "loss": 0.2112,
+      "step": 1250
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 6.365e-07,
+      "loss": 0.1231,
+      "step": 1275
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.49e-07,
+      "loss": 0.1914,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.614999999999999e-07,
+      "loss": 0.1485,
+      "step": 1325
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.74e-07,
+      "loss": 0.1958,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.865e-07,
+      "loss": 0.1452,
+      "step": 1375
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 6.989999999999999e-07,
+      "loss": 0.1624,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.115e-07,
+      "loss": 0.1518,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.24e-07,
+      "loss": 0.1935,
+      "step": 1450
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.365e-07,
+      "loss": 0.1138,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.489999999999999e-07,
+      "loss": 0.16,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.614999999999999e-07,
+      "loss": 0.1279,
+      "step": 1525
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 7.74e-07,
+      "loss": 0.1862,
+      "step": 1550
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 7.864999999999999e-07,
+      "loss": 0.1537,
+      "step": 1575
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 7.99e-07,
+      "loss": 0.1915,
+      "step": 1600
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.115e-07,
+      "loss": 0.1303,
+      "step": 1625
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.24e-07,
+      "loss": 0.1967,
+      "step": 1650
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.365e-07,
+      "loss": 0.1418,
+      "step": 1675
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.489999999999999e-07,
+      "loss": 0.194,
+      "step": 1700
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.615e-07,
+      "loss": 0.1377,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.739999999999999e-07,
+      "loss": 0.1534,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.864999999999999e-07,
+      "loss": 0.1416,
+      "step": 1775
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.99e-07,
+      "loss": 0.1869,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.115e-07,
+      "loss": 0.1507,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.24e-07,
+      "loss": 0.1571,
+      "step": 1850
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.365e-07,
+      "loss": 0.1348,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.489999999999999e-07,
+      "loss": 0.1981,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.615e-07,
+      "loss": 0.1324,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.74e-07,
+      "loss": 0.1712,
+      "step": 1950
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.865e-07,
+      "loss": 0.1169,
+      "step": 1975
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.989999999999999e-07,
+      "loss": 0.1654,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.1500108540058136,
+      "eval_runtime": 188234.7285,
+      "eval_samples_per_second": 0.05,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.10521978021978022,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 5.435997290496e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2000/training_args.bin b/checkpoint-2000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f9b2ac6d109ba135c37e8de1802d3dfa05ab0bb5
Binary files /dev/null and b/checkpoint-2000/training_args.bin differ
diff --git a/checkpoint-3000/config.json b/checkpoint-3000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..caa8aea5ccb9a4c479137c1f0ded8dc3bcc33fb2
--- /dev/null
+++ b/checkpoint-3000/config.json
@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "openai/whisper-large-v3",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": true,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}
diff --git a/checkpoint-3000/generation_config.json b/checkpoint-3000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9c184c23d34e10a8eb965f82773d9f8e3fb90c3d
--- /dev/null
+++ b/checkpoint-3000/generation_config.json
@@ -0,0 +1,264 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50360
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 1,
+  "max_length": 448,
+  "no_timestamps_token_id": 50364,
+  "pad_token_id": 50257,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.37.0.dev0"
+}
diff --git a/checkpoint-3000/model-00001-of-00002.safetensors b/checkpoint-3000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..48abeb97342dc287671ab8939818dcd3a2068f9f
--- /dev/null
+++ b/checkpoint-3000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f878789c48bcae8bdb738a21db184b61ea25d207190b7a28b1886fd661820964
+size 4993448880
diff --git a/checkpoint-3000/model-00002-of-00002.safetensors b/checkpoint-3000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5e22e7b0291e3a54a8a4dac84bf7b5ba5c977fa6
--- /dev/null
+++ b/checkpoint-3000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cebf488a1c5179e1630e18b09c98e0fc49f633401cd2860996acc46e8ce31123
+size 1180663192
diff --git a/checkpoint-3000/model.safetensors.index.json b/checkpoint-3000/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..c40d652c9b765dc6b1f8a90b16063b93b7b5c888
--- /dev/null
+++ b/checkpoint-3000/model.safetensors.index.json
@@ -0,0 +1,1266 @@
+{
+  "metadata": {
+    "total_size": 6173962240
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors"
+  }
+}
diff --git a/checkpoint-3000/optimizer.pt b/checkpoint-3000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6a5b2845f886a012b9e8966befc8fd0a50218a02
--- /dev/null
+++ b/checkpoint-3000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b881cb7e883293384811c41e69a3af5ab73194ee3fd9c7fc959db40efbb8dce
+size 12333660476
diff --git a/checkpoint-3000/preprocessor_config.json b/checkpoint-3000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f
--- /dev/null
+++ b/checkpoint-3000/preprocessor_config.json
@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-3000/rng_state.pth b/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..843248eeeac0b73ed09791b65fc502facef80e89
Binary files /dev/null and b/checkpoint-3000/rng_state.pth differ
diff --git a/checkpoint-3000/scheduler.pt b/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0dab76b6f4d51ae75eff90b97093c0661c1ef541
Binary files /dev/null and b/checkpoint-3000/scheduler.pt differ
diff --git a/checkpoint-3000/trainer_state.json b/checkpoint-3000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..45c5deb81b9903f9b7f2cbdf1450c03bcfeb6b4c
--- /dev/null
+++ b/checkpoint-3000/trainer_state.json
@@ -0,0 +1,768 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7741935483870968,
+  "eval_steps": 1000,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1499999999999999e-08,
+      "loss": 0.7822,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-08,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6499999999999996e-08,
+      "loss": 0.7809,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9e-08,
+      "loss": 1.2916,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.15e-08,
+      "loss": 0.7645,
+      "step": 125
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.399999999999999e-08,
+      "loss": 1.3379,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.649999999999999e-08,
+      "loss": 0.7722,
+      "step": 175
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.9e-08,
+      "loss": 1.281,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.115e-07,
+      "loss": 0.6998,
+      "step": 225
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.24e-07,
+      "loss": 1.1532,
+      "step": 250
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.365e-07,
+      "loss": 0.583,
+      "step": 275
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.49e-07,
+      "loss": 0.6693,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.615e-07,
+      "loss": 0.3395,
+      "step": 325
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7399999999999997e-07,
+      "loss": 0.3597,
+      "step": 350
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.8649999999999998e-07,
+      "loss": 0.22,
+      "step": 375
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.99e-07,
+      "loss": 0.3449,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.1149999999999998e-07,
+      "loss": 0.2123,
+      "step": 425
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.24e-07,
+      "loss": 0.3362,
+      "step": 450
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.3649999999999998e-07,
+      "loss": 0.175,
+      "step": 475
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.4899999999999997e-07,
+      "loss": 0.3051,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.615e-07,
+      "loss": 0.176,
+      "step": 525
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.74e-07,
+      "loss": 0.2517,
+      "step": 550
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.865e-07,
+      "loss": 0.1863,
+      "step": 575
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9899999999999996e-07,
+      "loss": 0.2614,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.115e-07,
+      "loss": 0.1942,
+      "step": 625
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.24e-07,
+      "loss": 0.2901,
+      "step": 650
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.3650000000000003e-07,
+      "loss": 0.1587,
+      "step": 675
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.4899999999999996e-07,
+      "loss": 0.2128,
+      "step": 700
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.6149999999999995e-07,
+      "loss": 0.1647,
+      "step": 725
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.74e-07,
+      "loss": 0.2473,
+      "step": 750
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.8649999999999997e-07,
+      "loss": 0.1415,
+      "step": 775
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.99e-07,
+      "loss": 0.2367,
+      "step": 800
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.1149999999999995e-07,
+      "loss": 0.1498,
+      "step": 825
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.24e-07,
+      "loss": 0.2161,
+      "step": 850
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.3649999999999997e-07,
+      "loss": 0.144,
+      "step": 875
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.49e-07,
+      "loss": 0.2316,
+      "step": 900
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.615e-07,
+      "loss": 0.1449,
+      "step": 925
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.7399999999999993e-07,
+      "loss": 0.1513,
+      "step": 950
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.864999999999999e-07,
+      "loss": 0.1855,
+      "step": 975
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.99e-07,
+      "loss": 0.199,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.15628743171691895,
+      "eval_runtime": 184706.1006,
+      "eval_samples_per_second": 0.051,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.1124272786037492,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5.114999999999999e-07,
+      "loss": 0.1301,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 5.24e-07,
+      "loss": 0.2193,
+      "step": 1050
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.365e-07,
+      "loss": 0.1552,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.490000000000001e-07,
+      "loss": 0.1865,
+      "step": 1100
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 5.614999999999999e-07,
+      "loss": 0.1618,
+      "step": 1125
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.739999999999999e-07,
+      "loss": 0.2259,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.865e-07,
+      "loss": 0.1418,
+      "step": 1175
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5.989999999999999e-07,
+      "loss": 0.1916,
+      "step": 1200
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.115e-07,
+      "loss": 0.1295,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.24e-07,
+      "loss": 0.2112,
+      "step": 1250
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 6.365e-07,
+      "loss": 0.1231,
+      "step": 1275
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.49e-07,
+      "loss": 0.1914,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.614999999999999e-07,
+      "loss": 0.1485,
+      "step": 1325
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.74e-07,
+      "loss": 0.1958,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.865e-07,
+      "loss": 0.1452,
+      "step": 1375
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 6.989999999999999e-07,
+      "loss": 0.1624,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.115e-07,
+      "loss": 0.1518,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.24e-07,
+      "loss": 0.1935,
+      "step": 1450
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.365e-07,
+      "loss": 0.1138,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.489999999999999e-07,
+      "loss": 0.16,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.614999999999999e-07,
+      "loss": 0.1279,
+      "step": 1525
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 7.74e-07,
+      "loss": 0.1862,
+      "step": 1550
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 7.864999999999999e-07,
+      "loss": 0.1537,
+      "step": 1575
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 7.99e-07,
+      "loss": 0.1915,
+      "step": 1600
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.115e-07,
+      "loss": 0.1303,
+      "step": 1625
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.24e-07,
+      "loss": 0.1967,
+      "step": 1650
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.365e-07,
+      "loss": 0.1418,
+      "step": 1675
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.489999999999999e-07,
+      "loss": 0.194,
+      "step": 1700
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.615e-07,
+      "loss": 0.1377,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.739999999999999e-07,
+      "loss": 0.1534,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.864999999999999e-07,
+      "loss": 0.1416,
+      "step": 1775
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.99e-07,
+      "loss": 0.1869,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.115e-07,
+      "loss": 0.1507,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.24e-07,
+      "loss": 0.1571,
+      "step": 1850
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.365e-07,
+      "loss": 0.1348,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.489999999999999e-07,
+      "loss": 0.1981,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.615e-07,
+      "loss": 0.1324,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.74e-07,
+      "loss": 0.1712,
+      "step": 1950
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.865e-07,
+      "loss": 0.1169,
+      "step": 1975
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.989999999999999e-07,
+      "loss": 0.1654,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.1500108540058136,
+      "eval_runtime": 188234.7285,
+      "eval_samples_per_second": 0.05,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.10521978021978022,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.923333333333332e-07,
+      "loss": 0.1202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.84e-07,
+      "loss": 0.186,
+      "step": 2050
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.756666666666666e-07,
+      "loss": 0.1106,
+      "step": 2075
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.673333333333332e-07,
+      "loss": 0.1926,
+      "step": 2100
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.589999999999998e-07,
+      "loss": 0.1178,
+      "step": 2125
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.506666666666667e-07,
+      "loss": 0.1744,
+      "step": 2150
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.423333333333333e-07,
+      "loss": 0.1263,
+      "step": 2175
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.34e-07,
+      "loss": 0.1818,
+      "step": 2200
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.256666666666666e-07,
+      "loss": 0.1466,
+      "step": 2225
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.173333333333333e-07,
+      "loss": 0.1357,
+      "step": 2250
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.09e-07,
+      "loss": 0.148,
+      "step": 2275
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.006666666666666e-07,
+      "loss": 0.1684,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.923333333333333e-07,
+      "loss": 0.1368,
+      "step": 2325
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.839999999999999e-07,
+      "loss": 0.188,
+      "step": 2350
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.756666666666666e-07,
+      "loss": 0.1299,
+      "step": 2375
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.673333333333332e-07,
+      "loss": 0.1461,
+      "step": 2400
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.59e-07,
+      "loss": 0.1569,
+      "step": 2425
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.506666666666667e-07,
+      "loss": 0.1527,
+      "step": 2450
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.423333333333334e-07,
+      "loss": 0.1041,
+      "step": 2475
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.34e-07,
+      "loss": 0.157,
+      "step": 2500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.256666666666666e-07,
+      "loss": 0.1364,
+      "step": 2525
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.173333333333333e-07,
+      "loss": 0.1685,
+      "step": 2550
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.09e-07,
+      "loss": 0.1344,
+      "step": 2575
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 8.006666666666666e-07,
+      "loss": 0.1589,
+      "step": 2600
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.923333333333333e-07,
+      "loss": 0.1334,
+      "step": 2625
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.84e-07,
+      "loss": 0.1297,
+      "step": 2650
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.756666666666665e-07,
+      "loss": 0.1326,
+      "step": 2675
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.673333333333332e-07,
+      "loss": 0.179,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.59e-07,
+      "loss": 0.1242,
+      "step": 2725
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.506666666666667e-07,
+      "loss": 0.1714,
+      "step": 2750
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.423333333333333e-07,
+      "loss": 0.1503,
+      "step": 2775
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.34e-07,
+      "loss": 0.131,
+      "step": 2800
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.256666666666667e-07,
+      "loss": 0.118,
+      "step": 2825
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.173333333333333e-07,
+      "loss": 0.1729,
+      "step": 2850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.089999999999999e-07,
+      "loss": 0.1193,
+      "step": 2875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.006666666666666e-07,
+      "loss": 0.1723,
+      "step": 2900
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 6.923333333333333e-07,
+      "loss": 0.1393,
+      "step": 2925
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.84e-07,
+      "loss": 0.1259,
+      "step": 2950
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.756666666666666e-07,
+      "loss": 0.1228,
+      "step": 2975
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.673333333333334e-07,
+      "loss": 0.1794,
+      "step": 3000
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.13788852095603943,
+      "eval_runtime": 198193.9708,
+      "eval_samples_per_second": 0.047,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.09970911441499677,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 8.153995935744e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-3000/training_args.bin b/checkpoint-3000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..f9b2ac6d109ba135c37e8de1802d3dfa05ab0bb5
Binary files /dev/null and b/checkpoint-3000/training_args.bin differ
diff --git a/checkpoint-4000/config.json b/checkpoint-4000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..caa8aea5ccb9a4c479137c1f0ded8dc3bcc33fb2
--- /dev/null
+++ b/checkpoint-4000/config.json
@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "openai/whisper-large-v3",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": true,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}
diff --git a/checkpoint-4000/generation_config.json b/checkpoint-4000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..cea34a613684b7726186da2813a3ecb580705460
--- /dev/null
+++ b/checkpoint-4000/generation_config.json
@@ -0,0 +1,265 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50364,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.37.0.dev0"
+}
diff --git a/checkpoint-4000/model-00001-of-00002.safetensors b/checkpoint-4000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2cc9c49f461f301f3d100a0243f0f354aa4f6c82
--- /dev/null
+++ b/checkpoint-4000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fedb9cc896a6388bb4f5cddb373b7392782ec965512769af969c60e1af1a4e14
+size 4993448880
diff --git a/checkpoint-4000/model-00002-of-00002.safetensors b/checkpoint-4000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2f7cf5a93c975accb476a84757532fee9168d3a5
--- /dev/null
+++ b/checkpoint-4000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6b0edf383dba5a20a86c58366da587af2b11f57f3238809e22174428275ba2
+size 1180663192
diff --git a/checkpoint-4000/model.safetensors.index.json b/checkpoint-4000/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..c40d652c9b765dc6b1f8a90b16063b93b7b5c888
--- /dev/null
+++ b/checkpoint-4000/model.safetensors.index.json
@@ -0,0 +1,1266 @@
+{
+  "metadata": {
+    "total_size": 6173962240
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors"
+  }
+}
diff --git a/checkpoint-4000/optimizer.pt b/checkpoint-4000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..753dc7c457199a95ad495dbc075b876c88c0dc7f
--- /dev/null
+++ b/checkpoint-4000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e4f108eb5557c44d32434b4917e37c96c5a7f16fb94640266fc8260e5fd15e
+size 12333660476
diff --git a/checkpoint-4000/preprocessor_config.json b/checkpoint-4000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f
--- /dev/null
+++ b/checkpoint-4000/preprocessor_config.json
@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-4000/rng_state.pth b/checkpoint-4000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d308ddd3e170f9a065973619c69588d354b17428
Binary files /dev/null and b/checkpoint-4000/rng_state.pth differ
diff --git a/checkpoint-4000/scheduler.pt b/checkpoint-4000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7957b6d08765ac2c37d8acb447251265daccbacb
Binary files /dev/null and b/checkpoint-4000/scheduler.pt differ
diff --git a/checkpoint-4000/trainer_state.json b/checkpoint-4000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e94ed50cd002bc6fa2d9bbd01625b4414e209ea4
--- /dev/null
+++ b/checkpoint-4000/trainer_state.json
@@ -0,0 +1,1017 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.032258064516129,
+  "eval_steps": 1000,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1499999999999999e-08,
+      "loss": 0.7822,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-08,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6499999999999996e-08,
+      "loss": 0.7809,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9e-08,
+      "loss": 1.2916,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.15e-08,
+      "loss": 0.7645,
+      "step": 125
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.399999999999999e-08,
+      "loss": 1.3379,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.649999999999999e-08,
+      "loss": 0.7722,
+      "step": 175
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.9e-08,
+      "loss": 1.281,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.115e-07,
+      "loss": 0.6998,
+      "step": 225
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.24e-07,
+      "loss": 1.1532,
+      "step": 250
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.365e-07,
+      "loss": 0.583,
+      "step": 275
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.49e-07,
+      "loss": 0.6693,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.615e-07,
+      "loss": 0.3395,
+      "step": 325
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7399999999999997e-07,
+      "loss": 0.3597,
+      "step": 350
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.8649999999999998e-07,
+      "loss": 0.22,
+      "step": 375
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.99e-07,
+      "loss": 0.3449,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.1149999999999998e-07,
+      "loss": 0.2123,
+      "step": 425
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.24e-07,
+      "loss": 0.3362,
+      "step": 450
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.3649999999999998e-07,
+      "loss": 0.175,
+      "step": 475
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.4899999999999997e-07,
+      "loss": 0.3051,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.615e-07,
+      "loss": 0.176,
+      "step": 525
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.74e-07,
+      "loss": 0.2517,
+      "step": 550
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.865e-07,
+      "loss": 0.1863,
+      "step": 575
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9899999999999996e-07,
+      "loss": 0.2614,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.115e-07,
+      "loss": 0.1942,
+      "step": 625
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.24e-07,
+      "loss": 0.2901,
+      "step": 650
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.3650000000000003e-07,
+      "loss": 0.1587,
+      "step": 675
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.4899999999999996e-07,
+      "loss": 0.2128,
+      "step": 700
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.6149999999999995e-07,
+      "loss": 0.1647,
+      "step": 725
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.74e-07,
+      "loss": 0.2473,
+      "step": 750
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.8649999999999997e-07,
+      "loss": 0.1415,
+      "step": 775
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.99e-07,
+      "loss": 0.2367,
+      "step": 800
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.1149999999999995e-07,
+      "loss": 0.1498,
+      "step": 825
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.24e-07,
+      "loss": 0.2161,
+      "step": 850
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.3649999999999997e-07,
+      "loss": 0.144,
+      "step": 875
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.49e-07,
+      "loss": 0.2316,
+      "step": 900
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.615e-07,
+      "loss": 0.1449,
+      "step": 925
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.7399999999999993e-07,
+      "loss": 0.1513,
+      "step": 950
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.864999999999999e-07,
+      "loss": 0.1855,
+      "step": 975
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.99e-07,
+      "loss": 0.199,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.15628743171691895,
+      "eval_runtime": 184706.1006,
+      "eval_samples_per_second": 0.051,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.1124272786037492,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5.114999999999999e-07,
+      "loss": 0.1301,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 5.24e-07,
+      "loss": 0.2193,
+      "step": 1050
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.365e-07,
+      "loss": 0.1552,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.490000000000001e-07,
+      "loss": 0.1865,
+      "step": 1100
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 5.614999999999999e-07,
+      "loss": 0.1618,
+      "step": 1125
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.739999999999999e-07,
+      "loss": 0.2259,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.865e-07,
+      "loss": 0.1418,
+      "step": 1175
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5.989999999999999e-07,
+      "loss": 0.1916,
+      "step": 1200
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.115e-07,
+      "loss": 0.1295,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.24e-07,
+      "loss": 0.2112,
+      "step": 1250
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 6.365e-07,
+      "loss": 0.1231,
+      "step": 1275
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.49e-07,
+      "loss": 0.1914,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.614999999999999e-07,
+      "loss": 0.1485,
+      "step": 1325
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.74e-07,
+      "loss": 0.1958,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.865e-07,
+      "loss": 0.1452,
+      "step": 1375
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 6.989999999999999e-07,
+      "loss": 0.1624,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.115e-07,
+      "loss": 0.1518,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.24e-07,
+      "loss": 0.1935,
+      "step": 1450
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.365e-07,
+      "loss": 0.1138,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.489999999999999e-07,
+      "loss": 0.16,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.614999999999999e-07,
+      "loss": 0.1279,
+      "step": 1525
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 7.74e-07,
+      "loss": 0.1862,
+      "step": 1550
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 7.864999999999999e-07,
+      "loss": 0.1537,
+      "step": 1575
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 7.99e-07,
+      "loss": 0.1915,
+      "step": 1600
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.115e-07,
+      "loss": 0.1303,
+      "step": 1625
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.24e-07,
+      "loss": 0.1967,
+      "step": 1650
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.365e-07,
+      "loss": 0.1418,
+      "step": 1675
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.489999999999999e-07,
+      "loss": 0.194,
+      "step": 1700
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.615e-07,
+      "loss": 0.1377,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.739999999999999e-07,
+      "loss": 0.1534,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.864999999999999e-07,
+      "loss": 0.1416,
+      "step": 1775
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.99e-07,
+      "loss": 0.1869,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.115e-07,
+      "loss": 0.1507,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.24e-07,
+      "loss": 0.1571,
+      "step": 1850
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.365e-07,
+      "loss": 0.1348,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.489999999999999e-07,
+      "loss": 0.1981,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.615e-07,
+      "loss": 0.1324,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.74e-07,
+      "loss": 0.1712,
+      "step": 1950
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.865e-07,
+      "loss": 0.1169,
+      "step": 1975
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.989999999999999e-07,
+      "loss": 0.1654,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.1500108540058136,
+      "eval_runtime": 188234.7285,
+      "eval_samples_per_second": 0.05,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.10521978021978022,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.923333333333332e-07,
+      "loss": 0.1202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.84e-07,
+      "loss": 0.186,
+      "step": 2050
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.756666666666666e-07,
+      "loss": 0.1106,
+      "step": 2075
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.673333333333332e-07,
+      "loss": 0.1926,
+      "step": 2100
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.589999999999998e-07,
+      "loss": 0.1178,
+      "step": 2125
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.506666666666667e-07,
+      "loss": 0.1744,
+      "step": 2150
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.423333333333333e-07,
+      "loss": 0.1263,
+      "step": 2175
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.34e-07,
+      "loss": 0.1818,
+      "step": 2200
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.256666666666666e-07,
+      "loss": 0.1466,
+      "step": 2225
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.173333333333333e-07,
+      "loss": 0.1357,
+      "step": 2250
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.09e-07,
+      "loss": 0.148,
+      "step": 2275
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.006666666666666e-07,
+      "loss": 0.1684,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.923333333333333e-07,
+      "loss": 0.1368,
+      "step": 2325
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.839999999999999e-07,
+      "loss": 0.188,
+      "step": 2350
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.756666666666666e-07,
+      "loss": 0.1299,
+      "step": 2375
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.673333333333332e-07,
+      "loss": 0.1461,
+      "step": 2400
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.59e-07,
+      "loss": 0.1569,
+      "step": 2425
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.506666666666667e-07,
+      "loss": 0.1527,
+      "step": 2450
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.423333333333334e-07,
+      "loss": 0.1041,
+      "step": 2475
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.34e-07,
+      "loss": 0.157,
+      "step": 2500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.256666666666666e-07,
+      "loss": 0.1364,
+      "step": 2525
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.173333333333333e-07,
+      "loss": 0.1685,
+      "step": 2550
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.09e-07,
+      "loss": 0.1344,
+      "step": 2575
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 8.006666666666666e-07,
+      "loss": 0.1589,
+      "step": 2600
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.923333333333333e-07,
+      "loss": 0.1334,
+      "step": 2625
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.84e-07,
+      "loss": 0.1297,
+      "step": 2650
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.756666666666665e-07,
+      "loss": 0.1326,
+      "step": 2675
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.673333333333332e-07,
+      "loss": 0.179,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.59e-07,
+      "loss": 0.1242,
+      "step": 2725
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.506666666666667e-07,
+      "loss": 0.1714,
+      "step": 2750
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.423333333333333e-07,
+      "loss": 0.1503,
+      "step": 2775
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.34e-07,
+      "loss": 0.131,
+      "step": 2800
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.256666666666667e-07,
+      "loss": 0.118,
+      "step": 2825
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.173333333333333e-07,
+      "loss": 0.1729,
+      "step": 2850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.089999999999999e-07,
+      "loss": 0.1193,
+      "step": 2875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.006666666666666e-07,
+      "loss": 0.1723,
+      "step": 2900
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 6.923333333333333e-07,
+      "loss": 0.1393,
+      "step": 2925
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.84e-07,
+      "loss": 0.1259,
+      "step": 2950
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.756666666666666e-07,
+      "loss": 0.1228,
+      "step": 2975
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.673333333333334e-07,
+      "loss": 0.1794,
+      "step": 3000
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.13788852095603943,
+      "eval_runtime": 198193.9708,
+      "eval_samples_per_second": 0.047,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.09970911441499677,
+      "step": 3000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.59e-07,
+      "loss": 0.1334,
+      "step": 3025
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.506666666666666e-07,
+      "loss": 0.1584,
+      "step": 3050
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.423333333333333e-07,
+      "loss": 0.1331,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.346666666666666e-07,
+      "loss": 0.1226,
+      "step": 3100
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.263333333333332e-07,
+      "loss": 0.135,
+      "step": 3125
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.18e-07,
+      "loss": 0.1538,
+      "step": 3150
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.096666666666667e-07,
+      "loss": 0.1405,
+      "step": 3175
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.013333333333334e-07,
+      "loss": 0.1534,
+      "step": 3200
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.93e-07,
+      "loss": 0.1628,
+      "step": 3225
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 5.846666666666667e-07,
+      "loss": 0.2002,
+      "step": 3250
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.763333333333333e-07,
+      "loss": 0.1155,
+      "step": 3275
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.679999999999999e-07,
+      "loss": 0.179,
+      "step": 3300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.596666666666666e-07,
+      "loss": 0.1471,
+      "step": 3325
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.513333333333333e-07,
+      "loss": 0.1386,
+      "step": 3350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.43e-07,
+      "loss": 0.1185,
+      "step": 3375
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.346666666666666e-07,
+      "loss": 0.1418,
+      "step": 3400
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.263333333333333e-07,
+      "loss": 0.1015,
+      "step": 3425
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.18e-07,
+      "loss": 0.1525,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.096666666666667e-07,
+      "loss": 0.1212,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.013333333333333e-07,
+      "loss": 0.1623,
+      "step": 3500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.93e-07,
+      "loss": 0.1178,
+      "step": 3525
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.846666666666667e-07,
+      "loss": 0.1618,
+      "step": 3550
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.763333333333333e-07,
+      "loss": 0.1187,
+      "step": 3575
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.68e-07,
+      "loss": 0.1382,
+      "step": 3600
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.5966666666666667e-07,
+      "loss": 0.1211,
+      "step": 3625
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.5133333333333327e-07,
+      "loss": 0.1582,
+      "step": 3650
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.43e-07,
+      "loss": 0.1201,
+      "step": 3675
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.3466666666666664e-07,
+      "loss": 0.1571,
+      "step": 3700
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.263333333333333e-07,
+      "loss": 0.1247,
+      "step": 3725
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.1799999999999996e-07,
+      "loss": 0.1648,
+      "step": 3750
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.0966666666666667e-07,
+      "loss": 0.1313,
+      "step": 3775
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.0133333333333333e-07,
+      "loss": 0.1528,
+      "step": 3800
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.93e-07,
+      "loss": 0.1252,
+      "step": 3825
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.8466666666666664e-07,
+      "loss": 0.1674,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.7633333333333335e-07,
+      "loss": 0.1192,
+      "step": 3875
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.6799999999999996e-07,
+      "loss": 0.1054,
+      "step": 3900
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.5966666666666667e-07,
+      "loss": 0.1353,
+      "step": 3925
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.5133333333333333e-07,
+      "loss": 0.1004,
+      "step": 3950
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.43e-07,
+      "loss": 0.1382,
+      "step": 3975
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.3466666666666665e-07,
+      "loss": 0.0821,
+      "step": 4000
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.13208560645580292,
+      "eval_runtime": 194476.4747,
+      "eval_samples_per_second": 0.048,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 1.000743374272786,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 1.0871315081330688e+20,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-4000/training_args.bin b/checkpoint-4000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..93e69a467867b9dbff737d816a19f85cc7227a5e
Binary files /dev/null and b/checkpoint-4000/training_args.bin differ
diff --git a/checkpoint-5000/config.json b/checkpoint-5000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..caa8aea5ccb9a4c479137c1f0ded8dc3bcc33fb2
--- /dev/null
+++ b/checkpoint-5000/config.json
@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "openai/whisper-large-v3",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": true,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": null,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}
diff --git a/checkpoint-5000/generation_config.json b/checkpoint-5000/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..cea34a613684b7726186da2813a3ecb580705460
--- /dev/null
+++ b/checkpoint-5000/generation_config.json
@@ -0,0 +1,265 @@
+{
+  "alignment_heads": [
+    [
+      7,
+      0
+    ],
+    [
+      10,
+      17
+    ],
+    [
+      12,
+      18
+    ],
+    [
+      13,
+      12
+    ],
+    [
+      16,
+      1
+    ],
+    [
+      17,
+      14
+    ],
+    [
+      19,
+      11
+    ],
+    [
+      21,
+      4
+    ],
+    [
+      24,
+      1
+    ],
+    [
+      25,
+      6
+    ]
+  ],
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "forced_decoder_ids": [
+    [
+      1,
+      null
+    ],
+    [
+      2,
+      50359
+    ]
+  ],
+  "is_multilingual": true,
+  "lang_to_id": {
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|yue|>": 50358,
+    "<|zh|>": 50260
+  },
+  "max_initial_timestamp_index": 50,
+  "max_length": 448,
+  "no_timestamps_token_id": 50364,
+  "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
+  "return_timestamps": false,
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50359,
+    50360,
+    50361,
+    50362,
+    50363
+  ],
+  "task_to_id": {
+    "transcribe": 50360,
+    "translate": 50359
+  },
+  "transformers_version": "4.37.0.dev0"
+}
diff --git a/checkpoint-5000/model-00001-of-00002.safetensors b/checkpoint-5000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0a2dd64e5f0a7cc597d6b5de6514e7ea2d91dad6
--- /dev/null
+++ b/checkpoint-5000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:162e92f863126b6badbad6104326cd65b2875f74bb0340e9b4d53e3d7cc4e83b
+size 4993448880
diff --git a/checkpoint-5000/model-00002-of-00002.safetensors b/checkpoint-5000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e583ef14471da6cdeca6620c93777120d9f7bfd3
--- /dev/null
+++ b/checkpoint-5000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3553cfea4d55a22ddc4554e797d5f41b8d4ec64eff37633af911cf87725f80
+size 1180663192
diff --git a/checkpoint-5000/model.safetensors.index.json b/checkpoint-5000/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..c40d652c9b765dc6b1f8a90b16063b93b7b5c888
--- /dev/null
+++ b/checkpoint-5000/model.safetensors.index.json
@@ -0,0 +1,1266 @@
+{
+  "metadata": {
+    "total_size": 6173962240
+  },
+  "weight_map": {
+    "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.24.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.25.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.26.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.27.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.28.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.29.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.30.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.encoder_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc1.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.fc2.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.conv2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.embed_positions.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "model.encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors"
+  }
+}
diff --git a/checkpoint-5000/optimizer.pt b/checkpoint-5000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..290099019ace04ffd23954be906dbdb5762d8863
--- /dev/null
+++ b/checkpoint-5000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f7fa7b096895a5ccb1902a0d8fec0c742bdca05c537aff90ca373cebe38514
+size 12333660476
diff --git a/checkpoint-5000/preprocessor_config.json b/checkpoint-5000/preprocessor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..931c77a740890c46365c7ae0c9d350ba3cca908f
--- /dev/null
+++ b/checkpoint-5000/preprocessor_config.json
@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}
diff --git a/checkpoint-5000/rng_state.pth b/checkpoint-5000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4f426eba0dc28e8fe02dc8a2bd18cc31e1922fd3
Binary files /dev/null and b/checkpoint-5000/rng_state.pth differ
diff --git a/checkpoint-5000/scheduler.pt b/checkpoint-5000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4aa391619e624e3b72edd58336913651ef08416d
Binary files /dev/null and b/checkpoint-5000/scheduler.pt differ
diff --git a/checkpoint-5000/trainer_state.json b/checkpoint-5000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4e826aad502d0c7403ef5d848a35d469090e9e19
--- /dev/null
+++ b/checkpoint-5000/trainer_state.json
@@ -0,0 +1,1266 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2903225806451613,
+  "eval_steps": 1000,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1499999999999999e-08,
+      "loss": 0.7822,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.4e-08,
+      "loss": 1.3149,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.6499999999999996e-08,
+      "loss": 0.7809,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9e-08,
+      "loss": 1.2916,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.15e-08,
+      "loss": 0.7645,
+      "step": 125
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.399999999999999e-08,
+      "loss": 1.3379,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.649999999999999e-08,
+      "loss": 0.7722,
+      "step": 175
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.9e-08,
+      "loss": 1.281,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.115e-07,
+      "loss": 0.6998,
+      "step": 225
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.24e-07,
+      "loss": 1.1532,
+      "step": 250
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.365e-07,
+      "loss": 0.583,
+      "step": 275
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.49e-07,
+      "loss": 0.6693,
+      "step": 300
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.615e-07,
+      "loss": 0.3395,
+      "step": 325
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.7399999999999997e-07,
+      "loss": 0.3597,
+      "step": 350
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.8649999999999998e-07,
+      "loss": 0.22,
+      "step": 375
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.99e-07,
+      "loss": 0.3449,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2.1149999999999998e-07,
+      "loss": 0.2123,
+      "step": 425
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.24e-07,
+      "loss": 0.3362,
+      "step": 450
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2.3649999999999998e-07,
+      "loss": 0.175,
+      "step": 475
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.4899999999999997e-07,
+      "loss": 0.3051,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.615e-07,
+      "loss": 0.176,
+      "step": 525
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 2.74e-07,
+      "loss": 0.2517,
+      "step": 550
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.865e-07,
+      "loss": 0.1863,
+      "step": 575
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.9899999999999996e-07,
+      "loss": 0.2614,
+      "step": 600
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 3.115e-07,
+      "loss": 0.1942,
+      "step": 625
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.24e-07,
+      "loss": 0.2901,
+      "step": 650
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.3650000000000003e-07,
+      "loss": 0.1587,
+      "step": 675
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 3.4899999999999996e-07,
+      "loss": 0.2128,
+      "step": 700
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.6149999999999995e-07,
+      "loss": 0.1647,
+      "step": 725
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.74e-07,
+      "loss": 0.2473,
+      "step": 750
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.8649999999999997e-07,
+      "loss": 0.1415,
+      "step": 775
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.99e-07,
+      "loss": 0.2367,
+      "step": 800
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.1149999999999995e-07,
+      "loss": 0.1498,
+      "step": 825
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.24e-07,
+      "loss": 0.2161,
+      "step": 850
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.3649999999999997e-07,
+      "loss": 0.144,
+      "step": 875
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.49e-07,
+      "loss": 0.2316,
+      "step": 900
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.615e-07,
+      "loss": 0.1449,
+      "step": 925
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.7399999999999993e-07,
+      "loss": 0.1513,
+      "step": 950
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.864999999999999e-07,
+      "loss": 0.1855,
+      "step": 975
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.99e-07,
+      "loss": 0.199,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.15628743171691895,
+      "eval_runtime": 184706.1006,
+      "eval_samples_per_second": 0.051,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.1124272786037492,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 5.114999999999999e-07,
+      "loss": 0.1301,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 5.24e-07,
+      "loss": 0.2193,
+      "step": 1050
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.365e-07,
+      "loss": 0.1552,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 5.490000000000001e-07,
+      "loss": 0.1865,
+      "step": 1100
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 5.614999999999999e-07,
+      "loss": 0.1618,
+      "step": 1125
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.739999999999999e-07,
+      "loss": 0.2259,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 5.865e-07,
+      "loss": 0.1418,
+      "step": 1175
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 5.989999999999999e-07,
+      "loss": 0.1916,
+      "step": 1200
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.115e-07,
+      "loss": 0.1295,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.24e-07,
+      "loss": 0.2112,
+      "step": 1250
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 6.365e-07,
+      "loss": 0.1231,
+      "step": 1275
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.49e-07,
+      "loss": 0.1914,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 6.614999999999999e-07,
+      "loss": 0.1485,
+      "step": 1325
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.74e-07,
+      "loss": 0.1958,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 6.865e-07,
+      "loss": 0.1452,
+      "step": 1375
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 6.989999999999999e-07,
+      "loss": 0.1624,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.115e-07,
+      "loss": 0.1518,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 7.24e-07,
+      "loss": 0.1935,
+      "step": 1450
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 7.365e-07,
+      "loss": 0.1138,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.489999999999999e-07,
+      "loss": 0.16,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 7.614999999999999e-07,
+      "loss": 0.1279,
+      "step": 1525
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 7.74e-07,
+      "loss": 0.1862,
+      "step": 1550
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 7.864999999999999e-07,
+      "loss": 0.1537,
+      "step": 1575
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 7.99e-07,
+      "loss": 0.1915,
+      "step": 1600
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 8.115e-07,
+      "loss": 0.1303,
+      "step": 1625
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.24e-07,
+      "loss": 0.1967,
+      "step": 1650
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 8.365e-07,
+      "loss": 0.1418,
+      "step": 1675
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 8.489999999999999e-07,
+      "loss": 0.194,
+      "step": 1700
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.615e-07,
+      "loss": 0.1377,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 8.739999999999999e-07,
+      "loss": 0.1534,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.864999999999999e-07,
+      "loss": 0.1416,
+      "step": 1775
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.99e-07,
+      "loss": 0.1869,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.115e-07,
+      "loss": 0.1507,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.24e-07,
+      "loss": 0.1571,
+      "step": 1850
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.365e-07,
+      "loss": 0.1348,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.489999999999999e-07,
+      "loss": 0.1981,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.615e-07,
+      "loss": 0.1324,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.74e-07,
+      "loss": 0.1712,
+      "step": 1950
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.865e-07,
+      "loss": 0.1169,
+      "step": 1975
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.989999999999999e-07,
+      "loss": 0.1654,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "eval_loss": 0.1500108540058136,
+      "eval_runtime": 188234.7285,
+      "eval_samples_per_second": 0.05,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.10521978021978022,
+      "step": 2000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.923333333333332e-07,
+      "loss": 0.1202,
+      "step": 2025
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.84e-07,
+      "loss": 0.186,
+      "step": 2050
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.756666666666666e-07,
+      "loss": 0.1106,
+      "step": 2075
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.673333333333332e-07,
+      "loss": 0.1926,
+      "step": 2100
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.589999999999998e-07,
+      "loss": 0.1178,
+      "step": 2125
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.506666666666667e-07,
+      "loss": 0.1744,
+      "step": 2150
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.423333333333333e-07,
+      "loss": 0.1263,
+      "step": 2175
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.34e-07,
+      "loss": 0.1818,
+      "step": 2200
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.256666666666666e-07,
+      "loss": 0.1466,
+      "step": 2225
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.173333333333333e-07,
+      "loss": 0.1357,
+      "step": 2250
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.09e-07,
+      "loss": 0.148,
+      "step": 2275
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.006666666666666e-07,
+      "loss": 0.1684,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.923333333333333e-07,
+      "loss": 0.1368,
+      "step": 2325
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.839999999999999e-07,
+      "loss": 0.188,
+      "step": 2350
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 8.756666666666666e-07,
+      "loss": 0.1299,
+      "step": 2375
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.673333333333332e-07,
+      "loss": 0.1461,
+      "step": 2400
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.59e-07,
+      "loss": 0.1569,
+      "step": 2425
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.506666666666667e-07,
+      "loss": 0.1527,
+      "step": 2450
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.423333333333334e-07,
+      "loss": 0.1041,
+      "step": 2475
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.34e-07,
+      "loss": 0.157,
+      "step": 2500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.256666666666666e-07,
+      "loss": 0.1364,
+      "step": 2525
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.173333333333333e-07,
+      "loss": 0.1685,
+      "step": 2550
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.09e-07,
+      "loss": 0.1344,
+      "step": 2575
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 8.006666666666666e-07,
+      "loss": 0.1589,
+      "step": 2600
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.923333333333333e-07,
+      "loss": 0.1334,
+      "step": 2625
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.84e-07,
+      "loss": 0.1297,
+      "step": 2650
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 7.756666666666665e-07,
+      "loss": 0.1326,
+      "step": 2675
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.673333333333332e-07,
+      "loss": 0.179,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.59e-07,
+      "loss": 0.1242,
+      "step": 2725
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 7.506666666666667e-07,
+      "loss": 0.1714,
+      "step": 2750
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.423333333333333e-07,
+      "loss": 0.1503,
+      "step": 2775
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.34e-07,
+      "loss": 0.131,
+      "step": 2800
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.256666666666667e-07,
+      "loss": 0.118,
+      "step": 2825
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.173333333333333e-07,
+      "loss": 0.1729,
+      "step": 2850
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.089999999999999e-07,
+      "loss": 0.1193,
+      "step": 2875
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.006666666666666e-07,
+      "loss": 0.1723,
+      "step": 2900
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 6.923333333333333e-07,
+      "loss": 0.1393,
+      "step": 2925
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.84e-07,
+      "loss": 0.1259,
+      "step": 2950
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.756666666666666e-07,
+      "loss": 0.1228,
+      "step": 2975
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.673333333333334e-07,
+      "loss": 0.1794,
+      "step": 3000
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.13788852095603943,
+      "eval_runtime": 198193.9708,
+      "eval_samples_per_second": 0.047,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 0.09970911441499677,
+      "step": 3000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 6.59e-07,
+      "loss": 0.1334,
+      "step": 3025
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.506666666666666e-07,
+      "loss": 0.1584,
+      "step": 3050
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 6.423333333333333e-07,
+      "loss": 0.1331,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 6.346666666666666e-07,
+      "loss": 0.1226,
+      "step": 3100
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.263333333333332e-07,
+      "loss": 0.135,
+      "step": 3125
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 6.18e-07,
+      "loss": 0.1538,
+      "step": 3150
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.096666666666667e-07,
+      "loss": 0.1405,
+      "step": 3175
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 6.013333333333334e-07,
+      "loss": 0.1534,
+      "step": 3200
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.93e-07,
+      "loss": 0.1628,
+      "step": 3225
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 5.846666666666667e-07,
+      "loss": 0.2002,
+      "step": 3250
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.763333333333333e-07,
+      "loss": 0.1155,
+      "step": 3275
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 5.679999999999999e-07,
+      "loss": 0.179,
+      "step": 3300
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.596666666666666e-07,
+      "loss": 0.1471,
+      "step": 3325
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.513333333333333e-07,
+      "loss": 0.1386,
+      "step": 3350
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 5.43e-07,
+      "loss": 0.1185,
+      "step": 3375
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.346666666666666e-07,
+      "loss": 0.1418,
+      "step": 3400
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.263333333333333e-07,
+      "loss": 0.1015,
+      "step": 3425
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.18e-07,
+      "loss": 0.1525,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.096666666666667e-07,
+      "loss": 0.1212,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.013333333333333e-07,
+      "loss": 0.1623,
+      "step": 3500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.93e-07,
+      "loss": 0.1178,
+      "step": 3525
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.846666666666667e-07,
+      "loss": 0.1618,
+      "step": 3550
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.763333333333333e-07,
+      "loss": 0.1187,
+      "step": 3575
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.68e-07,
+      "loss": 0.1382,
+      "step": 3600
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.5966666666666667e-07,
+      "loss": 0.1211,
+      "step": 3625
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.5133333333333327e-07,
+      "loss": 0.1582,
+      "step": 3650
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.43e-07,
+      "loss": 0.1201,
+      "step": 3675
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 4.3466666666666664e-07,
+      "loss": 0.1571,
+      "step": 3700
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.263333333333333e-07,
+      "loss": 0.1247,
+      "step": 3725
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.1799999999999996e-07,
+      "loss": 0.1648,
+      "step": 3750
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.0966666666666667e-07,
+      "loss": 0.1313,
+      "step": 3775
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.0133333333333333e-07,
+      "loss": 0.1528,
+      "step": 3800
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.93e-07,
+      "loss": 0.1252,
+      "step": 3825
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.8466666666666664e-07,
+      "loss": 0.1674,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.7633333333333335e-07,
+      "loss": 0.1192,
+      "step": 3875
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.6799999999999996e-07,
+      "loss": 0.1054,
+      "step": 3900
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.5966666666666667e-07,
+      "loss": 0.1353,
+      "step": 3925
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.5133333333333333e-07,
+      "loss": 0.1004,
+      "step": 3950
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.43e-07,
+      "loss": 0.1382,
+      "step": 3975
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.3466666666666665e-07,
+      "loss": 0.0821,
+      "step": 4000
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.13208560645580292,
+      "eval_runtime": 194476.4747,
+      "eval_samples_per_second": 0.048,
+      "eval_steps_per_second": 0.006,
+      "eval_wer": 1.000743374272786,
+      "step": 4000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.263333333333333e-07,
+      "loss": 0.1092,
+      "step": 4025
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.18e-07,
+      "loss": 0.0928,
+      "step": 4050
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.096666666666666e-07,
+      "loss": 0.1481,
+      "step": 4075
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.0133333333333333e-07,
+      "loss": 0.1043,
+      "step": 4100
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.93e-07,
+      "loss": 0.1018,
+      "step": 4125
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.8466666666666665e-07,
+      "loss": 0.104,
+      "step": 4150
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.763333333333333e-07,
+      "loss": 0.1394,
+      "step": 4175
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.68e-07,
+      "loss": 0.0962,
+      "step": 4200
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.596666666666666e-07,
+      "loss": 0.1058,
+      "step": 4225
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.5133333333333333e-07,
+      "loss": 0.0837,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.43e-07,
+      "loss": 0.1396,
+      "step": 4275
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.3466666666666665e-07,
+      "loss": 0.1005,
+      "step": 4300
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.263333333333333e-07,
+      "loss": 0.131,
+      "step": 4325
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.18e-07,
+      "loss": 0.1069,
+      "step": 4350
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.0966666666666665e-07,
+      "loss": 0.136,
+      "step": 4375
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.0133333333333334e-07,
+      "loss": 0.0954,
+      "step": 4400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.93e-07,
+      "loss": 0.1276,
+      "step": 4425
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.8466666666666665e-07,
+      "loss": 0.1033,
+      "step": 4450
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.7633333333333334e-07,
+      "loss": 0.1547,
+      "step": 4475
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.68e-07,
+      "loss": 0.1093,
+      "step": 4500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.5966666666666668e-07,
+      "loss": 0.1435,
+      "step": 4525
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.513333333333333e-07,
+      "loss": 0.1085,
+      "step": 4550
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4299999999999997e-07,
+      "loss": 0.1105,
+      "step": 4575
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3466666666666665e-07,
+      "loss": 0.0858,
+      "step": 4600
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.263333333333333e-07,
+      "loss": 0.1336,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.1799999999999998e-07,
+      "loss": 0.0857,
+      "step": 4650
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.0966666666666666e-07,
+      "loss": 0.1146,
+      "step": 4675
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.0133333333333333e-07,
+      "loss": 0.097,
+      "step": 4700
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 9.3e-08,
+      "loss": 0.1146,
+      "step": 4725
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 8.466666666666667e-08,
+      "loss": 0.0932,
+      "step": 4750
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.633333333333333e-08,
+      "loss": 0.1245,
+      "step": 4775
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.8e-08,
+      "loss": 0.0978,
+      "step": 4800
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.966666666666666e-08,
+      "loss": 0.1283,
+      "step": 4825
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.133333333333333e-08,
+      "loss": 0.1091,
+      "step": 4850
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.2999999999999995e-08,
+      "loss": 0.1106,
+      "step": 4875
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.4666666666666666e-08,
+      "loss": 0.1131,
+      "step": 4900
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.633333333333333e-08,
+      "loss": 0.1219,
+      "step": 4925
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8e-08,
+      "loss": 0.1205,
+      "step": 4950
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 9.666666666666667e-09,
+      "loss": 0.1408,
+      "step": 4975
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.3333333333333333e-09,
+      "loss": 0.1292,
+      "step": 5000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.132488414645195,
+      "eval_runtime": 160662.2084,
+      "eval_samples_per_second": 0.059,
+      "eval_steps_per_second": 0.007,
+      "eval_wer": 0.9998545572074984,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 1.3589313726578688e+20,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-5000/training_args.bin b/checkpoint-5000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..93e69a467867b9dbff737d816a19f85cc7227a5e
Binary files /dev/null and b/checkpoint-5000/training_args.bin differ
diff --git a/eval_results.json b/eval_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..79aa0add2af4ec8813b08411562b98eaabce78be
--- /dev/null
+++ b/eval_results.json
@@ -0,0 +1,9 @@
+{
+    "epoch": 1.29,
+    "eval_loss": 0.132488414645195,
+    "eval_runtime": 171706.1904,
+    "eval_samples": 9399,
+    "eval_samples_per_second": 0.055,
+    "eval_steps_per_second": 0.007,
+    "eval_wer": 0.9998545572074984
+}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
index 9c184c23d34e10a8eb965f82773d9f8e3fb90c3d..cea34a613684b7726186da2813a3ecb580705460 100644
--- a/generation_config.json
+++ b/generation_config.json
@@ -55,7 +55,7 @@
     ],
     [
       2,
-      50360
+      50359
     ]
   ],
   "is_multilingual": true,
@@ -161,10 +161,11 @@
     "<|yue|>": 50358,
     "<|zh|>": 50260
   },
-  "max_initial_timestamp_index": 1,
+  "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50364,
   "pad_token_id": 50257,
+  "prev_sot_token_id": 50362,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors
index 2cc9c49f461f301f3d100a0243f0f354aa4f6c82..0a2dd64e5f0a7cc597d6b5de6514e7ea2d91dad6 100644
--- a/model-00001-of-00002.safetensors
+++ b/model-00001-of-00002.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedb9cc896a6388bb4f5cddb373b7392782ec965512769af969c60e1af1a4e14
+oid sha256:162e92f863126b6badbad6104326cd65b2875f74bb0340e9b4d53e3d7cc4e83b
 size 4993448880
diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors
index 2f7cf5a93c975accb476a84757532fee9168d3a5..e583ef14471da6cdeca6620c93777120d9f7bfd3 100644
--- a/model-00002-of-00002.safetensors
+++ b/model-00002-of-00002.safetensors
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6b0edf383dba5a20a86c58366da587af2b11f57f3238809e22174428275ba2
+oid sha256:0a3553cfea4d55a22ddc4554e797d5f41b8d4ec64eff37633af911cf87725f80
 size 1180663192
diff --git a/runs/Feb01_13-09-49_DITEC2014063010/events.out.tfevents.1706804084.DITEC2014063010.17912.0 b/runs/Feb01_13-09-49_DITEC2014063010/events.out.tfevents.1706804084.DITEC2014063010.17912.0
index e899bc8097a46c22c256104695824fb3e30ce2fb..0c765727598d6ab6174eb7d1faf6a2f4b5557ef4 100644
Binary files a/runs/Feb01_13-09-49_DITEC2014063010/events.out.tfevents.1706804084.DITEC2014063010.17912.0 and b/runs/Feb01_13-09-49_DITEC2014063010/events.out.tfevents.1706804084.DITEC2014063010.17912.0 differ
diff --git a/runs/Feb05_12-30-35_DITEC2014063010/events.out.tfevents.1707147265.DITEC2014063010.20076.0 b/runs/Feb05_12-30-35_DITEC2014063010/events.out.tfevents.1707147265.DITEC2014063010.20076.0
index d86bb49a108490d57901141f586bd3c30af3e1a5..0a566ef14d8f2cdf2c444bee1a1e2213ab6d36ac 100644
Binary files a/runs/Feb05_12-30-35_DITEC2014063010/events.out.tfevents.1707147265.DITEC2014063010.20076.0 and b/runs/Feb05_12-30-35_DITEC2014063010/events.out.tfevents.1707147265.DITEC2014063010.20076.0 differ
diff --git a/runs/Feb05_12-30-35_DITEC2014063010/events.out.tfevents.1708496511.DITEC2014063010.20076.1 b/runs/Feb05_12-30-35_DITEC2014063010/events.out.tfevents.1708496511.DITEC2014063010.20076.1
index bfaf18bc3f1f8e7f9ac36fe9e4b1539448ecb72f..be10e1fbb2c169231ee49ccb295505ef04136c5d 100644
Binary files a/runs/Feb05_12-30-35_DITEC2014063010/events.out.tfevents.1708496511.DITEC2014063010.20076.1 and b/runs/Feb05_12-30-35_DITEC2014063010/events.out.tfevents.1708496511.DITEC2014063010.20076.1 differ
diff --git a/runs/Jan18_11-02-40_DITEC2014063010/events.out.tfevents.1705588605.DITEC2014063010.4840.0 b/runs/Jan18_11-02-40_DITEC2014063010/events.out.tfevents.1705588605.DITEC2014063010.4840.0
index 41c73bd33a87ba97ab7a4563731d7f370479539c..90b3fd3d4a6d30e11d393989901482674924a020 100644
Binary files a/runs/Jan18_11-02-40_DITEC2014063010/events.out.tfevents.1705588605.DITEC2014063010.4840.0 and b/runs/Jan18_11-02-40_DITEC2014063010/events.out.tfevents.1705588605.DITEC2014063010.4840.0 differ
diff --git a/train_results.json b/train_results.json
new file mode 100644
index 0000000000000000000000000000000000000000..71d2d980c29aacf726f1651ddf2ccab2c5abd069
--- /dev/null
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 1.29,
+    "train_loss": 0.05041759390830994,
+    "train_runtime": 1177508.0135,
+    "train_samples": 30998,
+    "train_samples_per_second": 0.034,
+    "train_steps_per_second": 0.004
+}
\ No newline at end of file
diff --git a/trainer_state.json b/trainer_state.json
index e94ed50cd002bc6fa2d9bbd01625b4414e209ea4..965fa11ac885f5fea6e8fdba72e0a0c54d821aa6 100644
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.032258064516129,
+  "epoch": 1.2903225806451613,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1003,6 +1003,264 @@
       "eval_steps_per_second": 0.006,
       "eval_wer": 1.000743374272786,
       "step": 4000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.263333333333333e-07,
+      "loss": 0.1092,
+      "step": 4025
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.18e-07,
+      "loss": 0.0928,
+      "step": 4050
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 3.096666666666666e-07,
+      "loss": 0.1481,
+      "step": 4075
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.0133333333333333e-07,
+      "loss": 0.1043,
+      "step": 4100
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.93e-07,
+      "loss": 0.1018,
+      "step": 4125
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 2.8466666666666665e-07,
+      "loss": 0.104,
+      "step": 4150
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.763333333333333e-07,
+      "loss": 0.1394,
+      "step": 4175
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.68e-07,
+      "loss": 0.0962,
+      "step": 4200
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 2.596666666666666e-07,
+      "loss": 0.1058,
+      "step": 4225
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.5133333333333333e-07,
+      "loss": 0.0837,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 2.43e-07,
+      "loss": 0.1396,
+      "step": 4275
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.3466666666666665e-07,
+      "loss": 0.1005,
+      "step": 4300
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.263333333333333e-07,
+      "loss": 0.131,
+      "step": 4325
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2.18e-07,
+      "loss": 0.1069,
+      "step": 4350
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 2.0966666666666665e-07,
+      "loss": 0.136,
+      "step": 4375
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 2.0133333333333334e-07,
+      "loss": 0.0954,
+      "step": 4400
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.93e-07,
+      "loss": 0.1276,
+      "step": 4425
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.8466666666666665e-07,
+      "loss": 0.1033,
+      "step": 4450
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.7633333333333334e-07,
+      "loss": 0.1547,
+      "step": 4475
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.68e-07,
+      "loss": 0.1093,
+      "step": 4500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.5966666666666668e-07,
+      "loss": 0.1435,
+      "step": 4525
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.513333333333333e-07,
+      "loss": 0.1085,
+      "step": 4550
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4299999999999997e-07,
+      "loss": 0.1105,
+      "step": 4575
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.3466666666666665e-07,
+      "loss": 0.0858,
+      "step": 4600
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.263333333333333e-07,
+      "loss": 0.1336,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.1799999999999998e-07,
+      "loss": 0.0857,
+      "step": 4650
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.0966666666666666e-07,
+      "loss": 0.1146,
+      "step": 4675
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.0133333333333333e-07,
+      "loss": 0.097,
+      "step": 4700
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 9.3e-08,
+      "loss": 0.1146,
+      "step": 4725
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 8.466666666666667e-08,
+      "loss": 0.0932,
+      "step": 4750
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 7.633333333333333e-08,
+      "loss": 0.1245,
+      "step": 4775
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.8e-08,
+      "loss": 0.0978,
+      "step": 4800
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.966666666666666e-08,
+      "loss": 0.1283,
+      "step": 4825
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.133333333333333e-08,
+      "loss": 0.1091,
+      "step": 4850
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.2999999999999995e-08,
+      "loss": 0.1106,
+      "step": 4875
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 3.4666666666666666e-08,
+      "loss": 0.1131,
+      "step": 4900
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.633333333333333e-08,
+      "loss": 0.1219,
+      "step": 4925
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.8e-08,
+      "loss": 0.1205,
+      "step": 4950
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 9.666666666666667e-09,
+      "loss": 0.1408,
+      "step": 4975
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.3333333333333333e-09,
+      "loss": 0.1292,
+      "step": 5000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.132488414645195,
+      "eval_runtime": 160662.2084,
+      "eval_samples_per_second": 0.059,
+      "eval_steps_per_second": 0.007,
+      "eval_wer": 0.9998545572074984,
+      "step": 5000
+    },
+    {
+      "epoch": 1.29,
+      "step": 5000,
+      "total_flos": 1.3589313726578688e+20,
+      "train_loss": 0.05041759390830994,
+      "train_runtime": 1177508.0135,
+      "train_samples_per_second": 0.034,
+      "train_steps_per_second": 0.004
     }
   ],
   "logging_steps": 25,
@@ -1010,7 +1268,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 1000,
-  "total_flos": 1.0871315081330688e+20,
+  "total_flos": 1.3589313726578688e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null
diff --git a/training_args.bin b/training_args.bin
index 55243e524c6b8e62c8516df3c33e0beaed5b29d9..93e69a467867b9dbff737d816a19f85cc7227a5e 100644
Binary files a/training_args.bin and b/training_args.bin differ