Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+tekken.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,97 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- it
+- pt
+- zh
+- ja
+- ru
+- ko
+license: apache-2.0
+library_name: vllm
+inference: false
+extra_gated_description: >-
+  If you want to learn more about how we process your personal data, please read
+  our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+tags:
+- transformers
+---
+
+Re-Uploaded without consolidated weights
+
+# Model Card for Mistral-Small-24B-Base-2501
+
+Mistral Small 3 ( 2501 ) sets a new benchmark in the "small" Large Language Models category below 70B, boasting 24B parameters and achieving state-of-the-art capabilities comparable to larger models!  
+Check out our fine-tuned Instruct version [Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501).
+
+For enterprises that need specialized capabilities (increased context, particular modalities, domain specific knowledge, etc.), we will be releasing commercial models beyond what Mistral AI contributes to the community.
+
+This release demonstrates our commitment to open source, serving as a strong base model. 
+
+Learn more about Mistral Small in our [blog post](https://mistral.ai/news/mistral-small-3/).
+
+Model developper: Mistral AI Team
+
+## Key Features
+- **Multilingual:** Supports dozens of languages, including English, French, German, Spanish, Italian, Chinese, Japanese, Korean, Portuguese, Dutch, and Polish.
+- **Advanced Reasoning:** State-of-the-art conversational and reasoning capabilities.
+- **Apache 2.0 License:** Open license allowing usage and modification for both commercial and non-commercial purposes.
+- **Context Window:** A 32k context window.
+- **Tokenizer:** Utilizes a Tekken tokenizer with a 131k vocabulary size.
+
+## Benchmark Results
+
+| Benchmark                      | Metric        | Mistral-Small-24B-Base |
+| ------------------------------ | ------------- | ----------- |
+| [MMLU][mmlu]                   | 5-shot        | 80.73        |
+| [MMLU Pro][mmlu_pro]         | 5-shot, CoT       | 54.37        |
+| [GPQA Main][gpqa]                   | 5-shot, CoT        | 34.37        |
+| [TriviaQA][triviaqa]         | 5-shot        | 80.32      |
+| [ARC-c][arc]                   | 0-shot       | 91.29        |
+| [TriviaQA][triviaqa]           | 5-shot        | 76.6        |
+| [MBPP][mbpp]                   | pass@1        | 69.64        |
+| [GSM8K][gsm8k]                 | 5-shot, maj@1 | 80.73        |
+| [MATH][math]                   | 4-shot, MaJ        | 45.98        |
+| [AGIEval][agieval]             | -      | 65.80        |
+
+| Benchmark                      | Metric        | Mistral-Small-24B-Base |
+| ------------------------------ | ------------- | ----------- |
+| French MMLU                    | -             | 78.03        |
+| German MMLU                    | -             | 77.69        |
+| Spanish MMLU                   | -             | 78.86        |
+| Russian MMLU                   | -             | 75.64        |
+| Chinese MMLU                   | -             | 70.35        |
+| Korean MMLU                    | -             | 56.42        |
+| Japanese MMLU                  | -             | 74.46        |
+
+
+[mmlu]: https://arxiv.org/abs/2009.03300
+[hellaswag]: https://arxiv.org/abs/1905.07830
+[piqa]: https://arxiv.org/abs/1911.11641
+[socialiqa]: https://arxiv.org/abs/1904.09728
+[boolq]: https://arxiv.org/abs/1905.10044
+[winogrande]: https://arxiv.org/abs/1907.10641
+[commonsenseqa]: https://arxiv.org/abs/1811.00937
+[openbookqa]: https://arxiv.org/abs/1809.02789
+[arc]: https://arxiv.org/abs/1911.01547
+[triviaqa]: https://arxiv.org/abs/1705.03551
+[naturalq]: https://github.com/google-research-datasets/natural-questions
+[humaneval]: https://arxiv.org/abs/2107.03374
+[mbpp]: https://arxiv.org/abs/2108.07732
+[gsm8k]: https://arxiv.org/abs/2110.14168
+[realtox]: https://arxiv.org/abs/2009.11462
+[bold]: https://arxiv.org/abs/2101.11718
+[crows]: https://aclanthology.org/2020.emnlp-main.154/
+[bbq]: https://arxiv.org/abs/2110.08193v2
+[winogender]: https://arxiv.org/abs/1804.09301
+[truthfulqa]: https://arxiv.org/abs/2109.07958
+[winobias]: https://arxiv.org/abs/1804.06876
+[math]: https://arxiv.org/abs/2103.03874
+[agieval]: https://arxiv.org/abs/2304.06364
+[big-bench]: https://arxiv.org/abs/2206.04615
+[toxigen]: https://arxiv.org/abs/2203.09509
+[mmlu_pro]: https://arxiv.org/abs/2406.01574
+[gpqa]: https://arxiv.org/abs/2311.12022

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 32768,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 100000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e4af7d1ccb727c3eb70c5e38b038fa3d80e97735c80f01aa40bad970418d77d
+size 4781571736

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58abfa3eac9302fad355e79f9fdadcf8bda3d8ab5b00d757e8b12dae21e0f788
+size 4781592784

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0626a2a93b7bd1c8bc384f1a1deaaf66c0778f15e6b6bf5bc13e23290f00aeb
+size 4781592800

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d60a86a6cd1f0c37f52e5d68af7d381cdb0ee5c53cfcf60d0ca60f73b35ce1
+size 4886471600

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7e46d096812a88481a6590c0b093376349e474144fdcf82b8a283844c36737
+size 4781592824

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b7aea96df5a738c056f66a492b073d0396e3ea1e70a4f6862e244675dc99558
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ab4431ed801e577e81d49e27a83e8d7bce6c94003053e87d1fc0ce38f5f617
+size 4886471600

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4778f58042fe43535c655a8effd776ac09fc76af8eb519675e35408f8648a4a0
+size 4781592824

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca4cc5d55cac267d4cccccf4369a804c0b8d7c7b7a3a3addcc6b3fcd7768d57
+size 4781592816

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927e0e995c26f6474aaddc6adb027d50414c4e7859b489d26f5e57b7b8168a7c
+size 3900777072

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 47144806400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00010-of-00010.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.norm.weight": "model-00010-of-00010.safetensors"
+  }
+}

params.json

@@ -0,0 +1,12 @@
+{
+    "dim": 5120,
+    "n_layers": 40,
+    "head_dim": 128,
+    "hidden_dim": 32768,
+    "n_heads": 32,
+    "n_kv_heads": 8,
+    "norm_eps": 1e-05,
+    "vocab_size": 131072,
+    "rope_theta": 100000000.0,
+    "max_seq_len": 32768
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b90a968dbc67ef3975129d0b78a2e3cbb6bea340ab9205f22e8a0308b1ffc5
+size 14801223

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
+size 17078037