Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,60 @@
+---
+base_model:
+- win10/EVA-QwQ-32B-Preview
+- ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
+- maldv/Qwentile2.5-32B-Instruct
+- Sao10K/32B-Qwen2.5-Kunou-v1
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merged
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the task_swapping merge method using [win10/EVA-QwQ-32B-Preview](https://huggingface.co/win10/EVA-QwQ-32B-Preview) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3](https://huggingface.co/ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3)
+* [maldv/Qwentile2.5-32B-Instruct](https://huggingface.co/maldv/Qwentile2.5-32B-Instruct)
+* [Sao10K/32B-Qwen2.5-Kunou-v1](https://huggingface.co/Sao10K/32B-Qwen2.5-Kunou-v1)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: win10/EVA-QwQ-32B-Preview
+dtype: bfloat16
+merge_method: task_swapping
+slices:
+- sources:
+  - layer_range: [0, 64]
+    model: maldv/Qwentile2.5-32B-Instruct
+    parameters:
+      diagonal_offset: 2.0
+      random_mask: 0.666
+      random_mask_seed: 888.0
+      weight: 0.5
+  - layer_range: [0, 64]
+    model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
+    parameters:
+      diagonal_offset: 5.0
+      weight: 0.75
+  - layer_range: [0, 64]
+    model: Sao10K/32B-Qwen2.5-Kunou-v1
+    parameters:
+      diagonal_offset: 2.0
+      random_mask: 0.333
+      random_mask_seed: 12347888.0
+      weight: 0.5
+  - layer_range: [0, 64]
+    model: win10/EVA-QwQ-32B-Preview
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "win10/EVA-QwQ-32B-Preview",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27648,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,26 @@
+base_model: win10/EVA-QwQ-32B-Preview
+dtype: bfloat16
+merge_method: task_swapping
+slices:
+- sources:
+  - layer_range: [0, 64]
+    model: maldv/Qwentile2.5-32B-Instruct
+    parameters:
+      diagonal_offset: 2.0
+      random_mask: 0.666
+      random_mask_seed: 888.0
+      weight: 0.5
+  - layer_range: [0, 64]
+    model: ArliAI/Qwen2.5-32B-ArliAI-RPMax-v1.3
+    parameters:
+      diagonal_offset: 5.0
+      weight: 0.75
+  - layer_range: [0, 64]
+    model: Sao10K/32B-Qwen2.5-Kunou-v1
+    parameters:
+      diagonal_offset: 2.0
+      random_mask: 0.333
+      random_mask_seed: 12347888.0
+      weight: 0.5
+  - layer_range: [0, 64]
+    model: win10/EVA-QwQ-32B-Preview

model-00001-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75dc3cd2316675c153d1a77477156241287fda6967d940ba9528743f54b0d5a
+size 1557135488

model-00002-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52ba2c1fc93458fa8834a58a95f11b06edc9005e8e1d5e3f74c86aa94be985c2
+size 2815473352

model-00003-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e543bfc0c86d712c9df3496f7e458aed10e0b6aa1716d95968c25049b61e754b
+size 2925635640

model-00004-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a058d5b6fd7bdcffc1ea30e0ab2ff1e4e69789396d3bdb5c0825a929b63c0479
+size 2925635648

model-00005-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f497fff9c3297c7c2d3c042816bbbfb60bedb3b2452c8b8bf2f63ed2e17736e0
+size 2925635648

model-00006-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce766e87b178e3ed7056b949301ecfe9cc2d7f571e2a6dd9ce5f5b8eb66bb36
+size 2925635640

model-00007-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8ebeb48e57e4f0c79896b2437e39f4c72fdaf7f656903e2a7e7d0e295db5d0
+size 2925635648

model-00008-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bd7d9f655e8766a933224543533237e01cc9736ba3c5d901829b8705635203
+size 2925635648

model-00009-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274e90308b2eb8a09ed0781a96f80b152f45d5a3223a9d28bca3062295c56a80
+size 2925635648

model-00010-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8434111efbd30b03e3986fb7240c5b31f4338ad01e97488cd9ebbb6f25cb95ba
+size 2925635640

model-00011-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e94e2b7d2f145aa2f77818606c43757651c6123ccf2e3f90a4d0149e91ba5ff
+size 2925635648

model-00012-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d16258e393b416348697e9150c927fc821e100822efa78478d74198904acc43
+size 2925635648

model-00013-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:068331a8617a42f447a07bddfbfa02712de279965187154bbc57772439dc96c7
+size 2925635648

model-00014-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b3965ebdb63118dd12a06d80d84a79b42e285c29f57e4d2f0dbaa62627148c
+size 2925635640

model-00015-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88dc77ea0651f367de69c7bd40ff28b6b72ca5ffd3ae2fcc76315eba4e1ffc93
+size 2925635648

model-00016-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6154f298d7e78c94684c0fd6cd4dfbbcdbaa41c225ebfd4e81908518e45e9c92
+size 2925635648

model-00017-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a7cbb35690eefa88a73e82f3c94b59d4fd8bc4b48bff584b4a5fb5927795a7f
+size 2925635640

model-00018-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62be1eed829602e62f98986757be0957f29e48ca04bd68c5533fc62fcfa21881
+size 2925635648

model-00019-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59abbc8a64c0869815a9776192737f158c620917139ed3771971ff857717c9ed
+size 2925635648

model-00020-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9092ad28118ee72c85c95232e70d93971770758fba331e2bfddf0c400a1c826
+size 2925635648

model-00021-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84cf3f7578b556d9fb5e75dec7f4de5db55d9f2376830956b9da716b8174bb3
+size 2925635640

model-00022-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b3e7c6b1157cf44b2921143f35ea4dd732e26951c17955f9a47dd5eca3df62
+size 2925635648

model-00023-of-00023.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef84b871a0c1db0c867bf50d23e842912335545fbb4ba15dcafb357f396dab2d
+size 2642519960

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 65527752704}, "weight_map": {"lm_head.weight": "model-00001-of-00023.safetensors", "model.embed_tokens.weight": "model-00002-of-00023.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00023.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00023.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00023.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00004-of-00023.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00023.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00023.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00023.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00023.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00023.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00023.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00023.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00023.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00023.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00023.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00023.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00023.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00023.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00023.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00023.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00023.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00023.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00023.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00023.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00023.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00023.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00023.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00023.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00023.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00023.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00023.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00023.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00023.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00023.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00023.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00023.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00010-of-00023.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00010-of-00023.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00023.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00023.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00023.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00023.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00023.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00023.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00011-of-00023.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00011-of-00023.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00011-of-00023.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00023.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00023.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00023.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00023.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00023.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00023.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00012-of-00023.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00012-of-00023.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00012-of-00023.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00023.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00023.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00023.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00023.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00023.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00023.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00013-of-00023.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00023.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00023.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00023.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00014-of-00023.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00014-of-00023.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00014-of-00023.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00014-of-00023.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.42.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00015-of-00023.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00015-of-00023.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00015-of-00023.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00015-of-00023.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00015-of-00023.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00015-of-00023.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00015-of-00023.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00015-of-00023.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00015-of-00023.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.45.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00016-of-00023.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00016-of-00023.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00016-of-00023.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00016-of-00023.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00016-of-00023.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00016-of-00023.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00016-of-00023.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00016-of-00023.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00016-of-00023.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.48.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00017-of-00023.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00017-of-00023.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00017-of-00023.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00017-of-00023.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00017-of-00023.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00017-of-00023.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.5.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00017-of-00023.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00017-of-00023.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00017-of-00023.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.50.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00018-of-00023.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00018-of-00023.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00018-of-00023.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.51.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00018-of-00023.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00018-of-00023.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00018-of-00023.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.52.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00018-of-00023.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00018-of-00023.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00018-of-00023.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.53.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00019-of-00023.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00019-of-00023.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00019-of-00023.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.54.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00019-of-00023.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00019-of-00023.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00019-of-00023.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.55.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00019-of-00023.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00019-of-00023.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00019-of-00023.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.56.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00020-of-00023.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00020-of-00023.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00020-of-00023.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.57.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00020-of-00023.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00020-of-00023.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00020-of-00023.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.58.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00020-of-00023.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00020-of-00023.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00020-of-00023.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.59.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00021-of-00023.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00021-of-00023.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00021-of-00023.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00021-of-00023.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.60.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00021-of-00023.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00021-of-00023.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00021-of-00023.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.61.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00022-of-00023.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00022-of-00023.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00022-of-00023.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.62.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00022-of-00023.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00022-of-00023.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00022-of-00023.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.63.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00022-of-00023.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00022-of-00023.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00022-of-00023.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00023-of-00023.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00023-of-00023.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00023-of-00023.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.input_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.input_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.norm.weight": "model-00023-of-00023.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}