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 +1,42 @@
+---
+base_model:
+- MaziyarPanahi/calme-3.2-instruct-78b
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [MaziyarPanahi/calme-3.2-instruct-78b](https://huggingface.co/MaziyarPanahi/calme-3.2-instruct-78b) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: MaziyarPanahi/calme-3.2-instruct-78b
+    parameters:
+      weight: 1
+      density: 1
+merge_method: ties
+base_model: MaziyarPanahi/calme-3.2-instruct-78b
+parameters:
+  weight: 1
+  density: 1
+  normalize: true
+  int8_mask: true
+dtype: float16
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "MaziyarPanahi/calme-3.2-instruct-78b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 86,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+models:
+  - model: MaziyarPanahi/calme-3.2-instruct-78b
+    parameters:
+      weight: 1
+      density: 1
+merge_method: ties
+base_model: MaziyarPanahi/calme-3.2-instruct-78b
+parameters:
+  weight: 1
+  density: 1
+  normalize: true
+  int8_mask: true
+dtype: float16

model-00001-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91a15a9bed33520c4b2da36931044d8a0e6a239291bf76ae5bf45ebbec24a57
+size 4969152856

model-00002-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7542719f6d9f8853217b5987070dfad8db2080942638f434d57a81ed08feec2b
+size 4980864368

model-00003-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ab786b8bcf13802f371481cf717eb2bf1818091152a77904cf81a00df56436
+size 4764874336

model-00004-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fbb9d68b0b8c0b48f6077ba5ca6edd05a4656eebb7bba0696f9451d013fb5e7
+size 4781670320

model-00005-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8dabb56c2bf8f3933e245b34da8018dc557c0fe1cdad5d8ce94fc8548574e8e
+size 4781670328

model-00006-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139efff2d4f4374471ed214560f55ef13d0a95733bc453985da71f1e93f11b13
+size 4980864384

model-00007-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c57baee75185b39174b0749ff2025ee7381be1b9c54c6dda829e275e59e314
+size 4764874336

model-00008-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8893b635dd26ece379d98e3d72f4113b25e03ba5d754e45079e4d378d69f8e3a
+size 4781670320

model-00009-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76bbb7ae91b5b75d8d81f2dc397f69080db6fc9e065e34cbb95fc2ee5ab6d370
+size 4781670328

model-00010-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21dd5ee9545b4bc261fc2548628bbc6acf99b3a823de2d365d031dc0f48897f
+size 4980864384

model-00011-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cac9d62a7e5d31f9eb0d62a1a453334f1e18965ca4d1242a23aa615939fb7a0
+size 4764874336

model-00012-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be35c88a145fbdd6bec9196d54329191dd9d9d1cab25963f0115f1fc33177a05
+size 4781670320

model-00013-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f350ac9b338e6ab93b3c82848f9e8cc96bd0d36fd1077398c1d5019f28ae09
+size 4781670328

model-00014-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8695230b03aa4d01742858d2516c85b4ac55407af198b5ba7ecf9b8f6fa8739b
+size 4980864384

model-00015-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3151131dcc69b9ef082c50e0e29fd4104a826fecd72cb322310b443d2d8af1a4
+size 4764874336

model-00016-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc3d8f3ae8641b1450359278c30735791f36d6c5b86c8001b48b8722c5f31cf
+size 4781670320

model-00017-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6975c2694e732cc18d67e1d8529122dd3a569558e598cf66bda7ded5715116d3
+size 4781670328

model-00018-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc59eb4c35dc5baef84203233136c7f8062b85d7d7e46937a2342db79ec514bf
+size 4980864384

model-00019-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46c2180d28eb4f716eebb38d14f11e0838c366b4140cfeaf9d5ada912327882
+size 4764874336

model-00020-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c657d9f76b8136f8dfbc8bf91f9ffc3957c1ff718e6fcb1dfeabddf1693d7cbc
+size 4781670320

model-00021-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39fb33441660fb0d9b60bc7bed2a88cf8a6d46982f24327d5d7c7938e71b9553
+size 4781670328

model-00022-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe0a7d52edcbe63136bca2c91fe89378dffd74dd0a4c0ac29398a9c244b1f7e
+size 4980864384

model-00023-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ed307255c38b68edb28a5efdfa924e27ba6dc297d3205a8d98ed53de178bb4
+size 4764874336

model-00024-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4330715afa3f2796bbed5ca6eea908759d14a68e837ae1ff68e857f4f56381cc
+size 4781670320

model-00025-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6617035ff047b780ee64229dfd6a490a47b4b8335cfd3a95f5af2628955084ee
+size 4781670328

model-00026-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f30309163a5616304baef037a596fa60bb6c81978839aa048a55c71b1e7c57c
+size 4980864384

model-00027-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096339250d797872d07430bfd53c413f0355ff2c5196a03bf0af2bb9ee6e495e
+size 4764874336

model-00028-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab07724cc671c0baf2aef716a0b500f6685bdfbc25756c7750bd6b29800e5b69
+size 4781670320

model-00029-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d8f5a9951c79ff554932670fb0e650f447d4aa61a1368bf3d1174d89c135f5
+size 4781670328

model-00030-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d03bc3126e0af8a367bb2adb7ff696cfe36236e3e1c135dad845580bee5a5f
+size 4980864384

model-00031-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e797fd990ab086d53e682997ce85c4ec158de7e0b94a4ec82b69dd09916b20a
+size 4764874336

model-00032-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:935aeb5924df28f475e1027dda3b47314137deb163f1bcce2320dfc442e810e4
+size 4781670320

model-00033-of-00033.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e42d9b9a24c7686e8aeda5450493e93f4f664a042dc0d02f2e5199b1d3c2ea
+size 1270928608

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 155930927104}, "weight_map": {"lm_head.weight": "model-00001-of-00033.safetensors", "model.embed_tokens.weight": "model-00001-of-00033.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00033.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00033.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00033.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00033.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00033.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00033.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00033.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00033.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00033.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00033.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00033.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00033.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00033.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00033.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00033.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00033.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00033.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00033.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00033.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00033.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00033.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00033.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00009-of-00033.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00033.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00033.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00010-of-00033.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00033.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00033.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00011-of-00033.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.input_layernorm.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00011-of-00033.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00012-of-00033.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00033.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00033.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00012-of-00033.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00013-of-00033.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00033.safetensors", "model.layers.39.input_layernorm.weight": "model-00013-of-00033.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00014-of-00033.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00033.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.input_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00014-of-00033.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00015-of-00033.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.input_layernorm.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00015-of-00033.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00016-of-00033.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00016-of-00033.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00033.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00033.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00017-of-00033.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00017-of-00033.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00033.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00018-of-00033.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00018-of-00033.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.input_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00033.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00019-of-00033.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.input_layernorm.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00019-of-00033.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00020-of-00033.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00033.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00033.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00020-of-00033.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00021-of-00033.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00033.safetensors", "model.layers.59.input_layernorm.weight": "model-00021-of-00033.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00022-of-00033.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00022-of-00033.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.input_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00033.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00023-of-00033.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.input_layernorm.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00033.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00024-of-00033.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00033.safetensors", "model.layers.66.input_layernorm.weight": "model-00024-of-00033.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00024-of-00033.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00025-of-00033.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00033.safetensors", "model.layers.69.input_layernorm.weight": "model-00025-of-00033.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00026-of-00033.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00026-of-00033.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.input_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00033.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00027-of-00033.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.input_layernorm.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00033.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00028-of-00033.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00033.safetensors", "model.layers.76.input_layernorm.weight": "model-00028-of-00033.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00028-of-00033.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00029-of-00033.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00033.safetensors", "model.layers.79.input_layernorm.weight": "model-00029-of-00033.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00030-of-00033.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.input_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00030-of-00033.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.input_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00030-of-00033.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00031-of-00033.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.input_layernorm.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00031-of-00033.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00032-of-00033.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00032-of-00033.safetensors", "model.layers.9.input_layernorm.weight": "model-00032-of-00033.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00032-of-00033.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00033-of-00033.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00033-of-00033.safetensors", "model.norm.weight": "model-00033-of-00033.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "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:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}