Add files using upload-large-folder tool

.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 +1,70 @@
+---
+inference: false
+library_name: transformers
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- ja
+- ko
+- zh
+- ar
+- el
+- fa
+- pl
+- id
+- cs
+- he
+- hi
+- nl
+- ro
+- ru
+- tr
+- uk
+- vi
+license: cc-by-nc-4.0
+extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license)  and
+  acknowledge that the information you provide will be collected, used, and shared
+  in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll
+  receive email updates about C4AI and Cohere research, events, products and services.
+  You can unsubscribe at any time.
+extra_gated_fields:
+  Name: text
+  Affiliation: text
+  Country: country
+  I agree to use this model for non-commercial use ONLY: checkbox
+base_model: CohereForAI/c4ai-command-a-03-2025
+tags:
+- mlx
+---
+
+# mlx-community/c4ai-command-a-03-2025-bf16
+
+The Model [mlx-community/c4ai-command-a-03-2025-bf16](https://huggingface.co/mlx-community/c4ai-command-a-03-2025-bf16) was
+converted to MLX format from [CohereForAI/c4ai-command-a-03-2025](https://huggingface.co/CohereForAI/c4ai-command-a-03-2025)
+using mlx-lm version **0.21.5**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/c4ai-command-a-03-2025-bf16")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

config.json

@@ -0,0 +1,38 @@
+{
+    "architectures": [
+        "Cohere2ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 5,
+    "cache_implementation": "hybrid",
+    "eos_token_id": 255001,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 12288,
+    "initializer_range": 0.02,
+    "intermediate_size": 36864,
+    "layer_norm_eps": 1e-05,
+    "logit_scale": 0.25,
+    "max_position_embeddings": 131072,
+    "model_type": "cohere2",
+    "num_attention_heads": 96,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "order_of_interleaved_layers": "local_attn_first",
+    "pad_token_id": 0,
+    "position_embedding_type": "rope_gptj",
+    "rope_scaling": null,
+    "rope_theta": 50000,
+    "rotary_pct": 1.0,
+    "sliding_window": 4096,
+    "sliding_window_pattern": 4,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.48.0.dev0",
+    "use_cache": true,
+    "use_embedding_sharing": true,
+    "use_gated_activation": true,
+    "use_parallel_block": true,
+    "use_parallel_embedding": true,
+    "vocab_size": 256000
+}

model-00001-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba4bb3ae3285d9746901116181c9bff31695e084001a2a77b3c49cddb35eb832
+size 41

model-00002-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96655dce2b5247af01f09110b5f6e6c07de7de29715299e1c44106dbee35b83f
+size 6291456139

model-00003-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb061cc1d525e3aed1cc680d0a7aa925a52117b0d78e01120cb455e78206b340
+size 4932527628

model-00004-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd3c721a4623e750f7f238672a2749c11f2288a98b38c879e49d9b814de8f88
+size 5184210190

model-00005-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e19b53ced034326972affb200a656d2d100a76a5c966471af1087085bc85f43
+size 4932527628

model-00006-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d7f6fb59c9a31d0f7e02471de0ef7f5ede5b848d128cbbc1eddb85332bee3d
+size 5184210190

model-00007-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993fe978fd7c4223269bcb1479dba0f5ae643cd765299701610217bba869c4de
+size 4932527622

model-00008-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6bdc569aaec31d82e5044a270f3e9a1a39682f363b76a1241235fdbc021149
+size 5184210200

model-00009-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b38bcb13398d5af862c0f144f91d328eda18a934d5308f9d0cfcaf5aa7e8e9
+size 4932527637

model-00010-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eadd179eca62933a7ebab88f00e61dd65604c0fe89f8f8d8810be31886ba8e0b
+size 5184210211

model-00011-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199d63f8976dccdbd0c925935affe6ce7ddec0e8b52c2364c90fafada154cec4
+size 4932527637

model-00012-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e416df764dfc178339746518faf801e566b97f9bcc4685bac717cb84e9917901
+size 5184210201

model-00013-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4783856e4e6db9e8ae7d15d6d2affeeacd0ff8726f07ed3903218bd847a5da3
+size 4932527641

model-00014-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d5a90a28a4b48c0d9b49cbfaa319ffc528b8abf7d2685e4fb3acb2f1f8f7aa
+size 5184210201

model-00015-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634e829dcbca0e1a6a4ae260245365d269fc0b043ddc3d44a8629acddf6abd81
+size 4932527639

model-00016-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1d4e26239ca034dd2c5b85299ab34c73b91143b5b98f6d5073b72ea0c07b96
+size 5184210201

model-00017-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54c4b470d955016f39b30e91d6e1ca8498ee552eebd4df311b4c93e968c3c5b
+size 4932527645

model-00018-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127367ed6b1cd099e72a0f5f7aff21899eea94e4bdaa454ef895dc8aa60c301c
+size 5184210201

model-00019-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cecd9c0e48e01be5e655be460d7e5af504319aca28668607eec2086a87ec38f
+size 4932527641

model-00020-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75199f48461c4a0681ca4fa5cd8f4fbc4551871b009c79476f4f460d9a036a8a
+size 5184210195

model-00021-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593657a2591fbc709db7701fbc7296d09658ca3229e5797c37a430c80711c7ec
+size 4932527641

model-00022-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb030212a1b77e5bca48e8ad8377a154c9724b6e3e6d9d690802715fc712e2a0
+size 5184210211

model-00023-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243f4099fd209fe5c52ef3e5be044055e2ff9c9e89eb53f5fc13cb3848ec605c
+size 4932527643

model-00024-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76561c38d14541959ccfa5b29dd4900f05e86d464c09358c19a2ee75cccd8ae8
+size 5184210205

model-00025-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb7ea010970ddc135dba09f91d1dd5d272477d436e4d0b91299f8da282d10c9
+size 4932527645

model-00026-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428a3fa37878f1ca3a5a0cc0d668e98a78995100c4db7f38ea164c7679fd61d0
+size 5184210201

model-00027-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0954adba8ab065e95db6a2938f1416429bad3c7f2b2f14d642f681fa20d05d9d
+size 4932527637

model-00028-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8046a4c9de404cfb4491ccf0f19f32cce21507c802e9e76a862f87d76d80918e
+size 5184210201

model-00029-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcb944ef9d9e3c172dbda412495cf035ce22032d9d755f7b8ea1b410cfe0313
+size 4932527641

model-00030-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b78bfbbad8b788bca65462e11ae64dba6b9df38d4da79016ffb6f338440099
+size 5184210211

model-00031-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feae89e2e53d772cbdbeeb788eb6d1405dc6db57ef3674c251f35af12fa9626c
+size 4932527645

model-00032-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab3b015e23a09914ec6be826f2c19b34b063ddfc72c5278fd245962b2c559b2
+size 5184210201

model-00033-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b916e38eb84c5055f10e675dd78a762ef066904c1d58bce1de109e29751e293d
+size 4932527643

model-00034-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880b1b4a62ef62794e934b1c361b068205670ed38089f72fddb936c56b4281c3
+size 5184210211

model-00035-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6ab0c1e25280944858df35f398564cdad3b8d020c51a0c8eafd9847469d1c9
+size 4932527637

model-00036-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261318b87e0811dc4c8867bab435dabc561a3994c89e6a8f3907bdcbb0d5bd7f
+size 5184210211

model-00037-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8680efee89532c12b302cef76f6005c5e7cc96e09feb0130879ae211b23c6f
+size 4932527637

model-00038-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c3a42b087c4fe819d92dbcfa4e45adf0aeb4673180e854bbb2f1bff3dc93aa6
+size 5184210209

model-00039-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357c41ed2b19f09090e9522f3178a7b9b4b971408993bb66cf9f8abb92a82277
+size 4932527635

model-00040-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0fea112eb44ee8b6665d39c07e80734f3f4079d9e35dd759692a1b0520991e
+size 5184210211

model-00041-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61452699141f6e0e9a96dc8f3641b8ab88377fb8b795524163fc0884dfa70791
+size 4932527641

model-00042-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00fb6d877e3bfdf3b88789b7740596e8c28358c8fbece0dc3c970acf7d36c6f
+size 5184210211

model-00043-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1f219afb2032b8750932f09a47d313e5d2ba1e9b73ccc9ad53b0b00ba0947a
+size 4932527645

model-00044-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe8536bdc34cb5a928e4dc89d8533f179afebde54e08db884014cdac3e21e0d
+size 5184210211

model-00045-of-00045.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0df4cfba517b4dff837ae8bbde420df8894b375f9b79ebbd514f9accbd9cd9d
+size 3372270610

model.safetensors.index.json

@@ -0,0 +1,521 @@
+{
+    "metadata": {
+        "total_size": 222115160064
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "model-00002-of-00045.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00003-of-00045.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00004-of-00045.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00004-of-00045.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00004-of-00045.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00045.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00010-of-00045.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00010-of-00045.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00010-of-00045.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00010-of-00045.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00010-of-00045.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00010-of-00045.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00010-of-00045.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00045.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00045.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00045.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00045.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00011-of-00045.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00012-of-00045.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00012-of-00045.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00012-of-00045.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00045.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00012-of-00045.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00012-of-00045.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00012-of-00045.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00012-of-00045.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00045.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00045.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00045.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00045.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00013-of-00045.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00014-of-00045.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00014-of-00045.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00014-of-00045.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00045.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00014-of-00045.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00014-of-00045.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00014-of-00045.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00014-of-00045.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00045.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00045.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00045.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00045.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00015-of-00045.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00016-of-00045.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00016-of-00045.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00016-of-00045.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00015-of-00045.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00004-of-00045.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00004-of-00045.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00045.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00004-of-00045.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00045.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00045.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00045.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00045.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00016-of-00045.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00016-of-00045.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00016-of-00045.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00016-of-00045.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00045.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00045.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00045.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00045.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00017-of-00045.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00018-of-00045.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00018-of-00045.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00018-of-00045.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00017-of-00045.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00018-of-00045.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00018-of-00045.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00018-of-00045.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00018-of-00045.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00045.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00045.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00045.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00018-of-00045.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00019-of-00045.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00020-of-00045.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00020-of-00045.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00020-of-00045.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00045.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00020-of-00045.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00020-of-00045.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00020-of-00045.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00020-of-00045.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00020-of-00045.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00020-of-00045.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00020-of-00045.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00020-of-00045.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00021-of-00045.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00022-of-00045.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00022-of-00045.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00022-of-00045.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00021-of-00045.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00022-of-00045.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00022-of-00045.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00022-of-00045.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00022-of-00045.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00022-of-00045.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00022-of-00045.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00022-of-00045.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00022-of-00045.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00005-of-00045.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00023-of-00045.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00024-of-00045.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00024-of-00045.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00024-of-00045.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00045.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00024-of-00045.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00024-of-00045.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00024-of-00045.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00024-of-00045.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00024-of-00045.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00024-of-00045.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00024-of-00045.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00024-of-00045.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00025-of-00045.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00026-of-00045.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00026-of-00045.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00026-of-00045.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00025-of-00045.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00026-of-00045.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00026-of-00045.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00026-of-00045.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00026-of-00045.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00026-of-00045.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00026-of-00045.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00026-of-00045.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00026-of-00045.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00027-of-00045.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00028-of-00045.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00028-of-00045.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00028-of-00045.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00027-of-00045.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00028-of-00045.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00028-of-00045.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00028-of-00045.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00028-of-00045.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00028-of-00045.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00028-of-00045.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00028-of-00045.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00028-of-00045.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00029-of-00045.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00006-of-00045.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00006-of-00045.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00006-of-00045.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00045.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00030-of-00045.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00030-of-00045.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00030-of-00045.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00029-of-00045.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00030-of-00045.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00030-of-00045.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00030-of-00045.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00030-of-00045.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00030-of-00045.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00030-of-00045.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00030-of-00045.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00030-of-00045.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00031-of-00045.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00032-of-00045.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00032-of-00045.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00032-of-00045.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00031-of-00045.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00032-of-00045.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00032-of-00045.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00032-of-00045.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00032-of-00045.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00032-of-00045.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00032-of-00045.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00032-of-00045.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00032-of-00045.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00033-of-00045.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00034-of-00045.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00034-of-00045.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00034-of-00045.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00033-of-00045.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00034-of-00045.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00034-of-00045.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00034-of-00045.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00034-of-00045.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00034-of-00045.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00034-of-00045.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00034-of-00045.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00034-of-00045.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00035-of-00045.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00036-of-00045.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00036-of-00045.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00036-of-00045.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00035-of-00045.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00006-of-00045.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00006-of-00045.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00045.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00006-of-00045.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00045.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00045.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00045.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00045.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00036-of-00045.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00036-of-00045.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00036-of-00045.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00036-of-00045.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00036-of-00045.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00036-of-00045.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00036-of-00045.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00036-of-00045.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00037-of-00045.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00038-of-00045.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00038-of-00045.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00038-of-00045.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00037-of-00045.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00038-of-00045.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00038-of-00045.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00038-of-00045.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00038-of-00045.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00038-of-00045.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00038-of-00045.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00038-of-00045.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00038-of-00045.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00039-of-00045.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00040-of-00045.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00040-of-00045.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00040-of-00045.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00039-of-00045.safetensors",
+        "model.layers.56.input_layernorm.weight": "model-00040-of-00045.safetensors",
+        "model.layers.56.mlp.down_proj.weight": "model-00040-of-00045.safetensors",
+        "model.layers.56.mlp.gate_proj.weight": "model-00040-of-00045.safetensors",
+        "model.layers.56.mlp.up_proj.weight": "model-00040-of-00045.safetensors",
+        "model.layers.56.self_attn.k_proj.weight": "model-00040-of-00045.safetensors",
+        "model.layers.56.self_attn.o_proj.weight": "model-00040-of-00045.safetensors",
+        "model.layers.56.self_attn.q_proj.weight": "model-00040-of-00045.safetensors",
+        "model.layers.56.self_attn.v_proj.weight": "model-00040-of-00045.safetensors",
+        "model.layers.57.input_layernorm.weight": "model-00041-of-00045.safetensors",
+        "model.layers.57.mlp.down_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.57.mlp.gate_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.57.mlp.up_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.57.self_attn.k_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.57.self_attn.o_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.57.self_attn.q_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.57.self_attn.v_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.58.input_layernorm.weight": "model-00042-of-00045.safetensors",
+        "model.layers.58.mlp.down_proj.weight": "model-00042-of-00045.safetensors",
+        "model.layers.58.mlp.gate_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.58.mlp.up_proj.weight": "model-00042-of-00045.safetensors",
+        "model.layers.58.self_attn.k_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.58.self_attn.o_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.58.self_attn.q_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.58.self_attn.v_proj.weight": "model-00041-of-00045.safetensors",
+        "model.layers.59.input_layernorm.weight": "model-00042-of-00045.safetensors",
+        "model.layers.59.mlp.down_proj.weight": "model-00042-of-00045.safetensors",
+        "model.layers.59.mlp.gate_proj.weight": "model-00042-of-00045.safetensors",
+        "model.layers.59.mlp.up_proj.weight": "model-00042-of-00045.safetensors",
+        "model.layers.59.self_attn.k_proj.weight": "model-00042-of-00045.safetensors",
+        "model.layers.59.self_attn.o_proj.weight": "model-00042-of-00045.safetensors",
+        "model.layers.59.self_attn.q_proj.weight": "model-00042-of-00045.safetensors",
+        "model.layers.59.self_attn.v_proj.weight": "model-00042-of-00045.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00007-of-00045.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.60.input_layernorm.weight": "model-00043-of-00045.safetensors",
+        "model.layers.60.mlp.down_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.60.mlp.gate_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.60.mlp.up_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.60.self_attn.k_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.60.self_attn.o_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.60.self_attn.q_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.60.self_attn.v_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.61.input_layernorm.weight": "model-00044-of-00045.safetensors",
+        "model.layers.61.mlp.down_proj.weight": "model-00044-of-00045.safetensors",
+        "model.layers.61.mlp.gate_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.61.mlp.up_proj.weight": "model-00044-of-00045.safetensors",
+        "model.layers.61.self_attn.k_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.61.self_attn.o_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.61.self_attn.q_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.61.self_attn.v_proj.weight": "model-00043-of-00045.safetensors",
+        "model.layers.62.input_layernorm.weight": "model-00044-of-00045.safetensors",
+        "model.layers.62.mlp.down_proj.weight": "model-00044-of-00045.safetensors",
+        "model.layers.62.mlp.gate_proj.weight": "model-00044-of-00045.safetensors",
+        "model.layers.62.mlp.up_proj.weight": "model-00044-of-00045.safetensors",
+        "model.layers.62.self_attn.k_proj.weight": "model-00044-of-00045.safetensors",
+        "model.layers.62.self_attn.o_proj.weight": "model-00044-of-00045.safetensors",
+        "model.layers.62.self_attn.q_proj.weight": "model-00044-of-00045.safetensors",
+        "model.layers.62.self_attn.v_proj.weight": "model-00044-of-00045.safetensors",
+        "model.layers.63.input_layernorm.weight": "model-00045-of-00045.safetensors",
+        "model.layers.63.mlp.down_proj.weight": "model-00045-of-00045.safetensors",
+        "model.layers.63.mlp.gate_proj.weight": "model-00045-of-00045.safetensors",
+        "model.layers.63.mlp.up_proj.weight": "model-00045-of-00045.safetensors",
+        "model.layers.63.self_attn.k_proj.weight": "model-00045-of-00045.safetensors",
+        "model.layers.63.self_attn.o_proj.weight": "model-00045-of-00045.safetensors",
+        "model.layers.63.self_attn.q_proj.weight": "model-00045-of-00045.safetensors",
+        "model.layers.63.self_attn.v_proj.weight": "model-00045-of-00045.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00008-of-00045.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00008-of-00045.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00008-of-00045.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00045.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00008-of-00045.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00008-of-00045.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00045.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00008-of-00045.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00045.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00045.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00045.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00045.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00009-of-00045.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00045.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00045.safetensors",
+        "model.norm.weight": "model-00045-of-00045.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<UNK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}