Super-squash branch 'main' using huggingface_hub

Co-authored-by: patrickvonplaten <[email protected]>

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,230 @@
+---
+language:
+- en
+- fr
+- de
+- es
+- pt
+- it
+- ja
+- ko
+- ru
+- zh
+- ar
+- fa
+- id
+- ms
+- ne
+- pl
+- ro
+- sr
+- sv
+- tr
+- uk
+- vi
+- hi
+- bn
+license: apache-2.0
+library_name: vllm
+inference: false
+base_model:
+- mistralai/Mistral-Small-3.1-24B-Instruct-2503
+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>.
+---
+
+# Model Card for Magistral-Small-2506
+
+Building upon Mistral Small 3.1 (2503), **with added reasoning capabilities**, undergoing SFT from Magistral Medium traces and RL on top, it's a small, efficient reasoning model with 24B parameters.
+
+Magistral Small can be deployed locally, fitting within a single RTX 4090 or a 32GB RAM MacBook once quantized.
+
+Learn more about Magistral in our [blog post](https://mistral.ai/news/magistral/).
+
+## Key Features
+- **Reasoning:** Capable of long chains of reasoning traces before providing an answer.
+- **Multilingual:** Supports dozens of languages, including English, French, German, Greek, Hindi, Indonesian, Italian, Japanese, Korean, Malay, Nepali, Polish, Portuguese, Romanian, Russian, Serbian, Spanish, Swedish, Turkish, Ukrainian, Vietnamese, Arabic, Bengali, Chinese, and Farsi.
+- **Apache 2.0 License:** Open license allowing usage and modification for both commercial and non-commercial purposes.
+- **Context Window:** A 128k context window, **but** performance might degrade past **40k**. Hence we recommend setting the maximum model length to 40k.
+
+## Benchmark Results
+
+| Model | AIME24 pass@1 | AIME25 pass@1 | GPQA Diamond | Livecodebench (v5) |
+|-------|-------------|-------------|--------------|-------------------|
+| Magistral Medium | 73.59% | 64.95% | 70.83% | 59.36% |
+| Magistral Small | 70.68% | 62.76% | 68.18% | 55.84% |
+
+## Sampling parameters
+
+Please make sure to use: 
+- `top_p`: 0.95
+- `temperature`: 0.7
+- `max_tokens`: 40960
+
+## Basic Chat Template
+
+We highly recommend including the default system prompt used during RL for the best results, you can edit and customise it if needed for your specific use case.
+
+```
+<s>[SYSTEM_PROMPT]system_prompt
+
+A user will ask you to solve a task. You should first draft your thinking process (inner monologue) until you have derived the final answer. Afterwards, write a self-contained summary of your thoughts (i.e. your summary should be succinct but contain all the critical steps you needed to reach the conclusion). You should use Markdown to format your response. Write both your thoughts and summary in the same language as the task posed by the user. NEVER use \boxed{} in your response.
+
+Your thinking process must follow the template below:
+<think>
+Your thoughts or/and draft, like working through an exercise on scratch paper. Be as casual and as long as you want until you are confident to generate a correct answer.
+</think>
+
+Here, provide a concise summary that reflects your reasoning and presents a clear final answer to the user. Don't mention that this is a summary.
+
+Problem:
+
+[/SYSTEM_PROMPT][INST]user_message[/INST]<think>
+reasoning_traces
+</think>
+assistant_response</s>[INST]user_message[/INST]
+```
+*`system_prompt`, `user_message` and `assistant_response` are placeholders.*
+
+We invite you to choose, depending on your use case and requirements, between keeping reasoning traces during multi-turn interactions or keeping only the final assistant response.
+
+***Please make sure to use [mistral-common](https://github.com/mistralai/mistral-common) as the source of truth***
+
+## Usage
+
+The model can be used with the following frameworks;
+
+### Inference
+
+- [`vllm (recommended)`](https://github.com/vllm-project/vllm): See [below](#vllm)
+
+In addition the community has prepared quantized versions of the model that can be used with the following frameworks (*alphabetically sorted*):
+- [`llama.cpp`](https://github.com/ggml-org/llama.cpp): https://huggingface.co/mistralai/Magistral-Small-2506_gguf
+- [`lmstudio` (llama.cpp)](https://lmstudio.ai/): https://lmstudio.ai/models/mistralai/magistral-small
+- [`ollama` (llama.cpp)](https://ollama.com/): https://ollama.com/library/magistral
+- [`unsloth` (llama.cpp)](https://huggingface.co/unsloth): https://huggingface.co/unsloth/Magistral-Small-2506-GGUF
+
+### Training
+
+Fine-tuning is possible with (*alphabetically sorted*):
+- [`axolotl`](https://github.com/axolotl-ai-cloud/axolotl): https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/magistral
+- [`unsloth`](https://github.com/unslothai/unsloth): https://docs.unsloth.ai/basics/magistral
+
+### Other
+
+Also you can use Magistral with:
+- [`kaggle`](https://www.kaggle.com/models/mistral-ai/magistral-small-2506): https://www.kaggle.com/models/mistral-ai/magistral-small-2506
+
+### vLLM (recommended)
+
+We recommend using this model with the [vLLM library](https://github.com/vllm-project/vllm)
+to implement production-ready inference pipelines.
+
+**_Installation_**
+
+Make sure you install the latest [`vLLM`](https://github.com/vllm-project/vllm/) code:
+
+```
+pip install -U vllm \
+    --pre \
+    --extra-index-url https://wheels.vllm.ai/nightly
+```
+
+Doing so should automatically install [`mistral_common >= 1.6.0`](https://github.com/mistralai/mistral-common/releases/tag/v1.6.0).
+
+To check:
+```
+python -c "import mistral_common; print(mistral_common.__version__)"
+```
+
+You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39).
+
+
+Serve model as follows:
+
+```
+vllm serve mistralai/Magistral-Small-2506 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2
+```
+
+Ping model as follows:
+
+```py
+from openai import OpenAI
+from huggingface_hub import hf_hub_download
+
+# Modify OpenAI's API key and API base to use vLLM's API server.
+openai_api_key = "EMPTY"
+openai_api_base = "http://localhost:8000/v1"
+
+TEMP = 0.7
+TOP_P = 0.95
+MAX_TOK = 40_960
+
+client = OpenAI(
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = hf_hub_download(repo_id=repo_id, filename=filename)
+    with open(file_path, "r") as file:
+        system_prompt = file.read()
+    return system_prompt
+
+SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
+
+query = "Write 4 sentences, each with at least 8 words. Now make absolutely sure that every sentence has exactly one word less than the previous sentence."
+# or try out other queries
+# query = "Exactly how many days ago did the French Revolution start? Today is June 4th, 2025."
+# query = "Think about 5 random numbers. Verify if you can combine them with addition, multiplication, subtraction or division to 133"
+# query = "If it takes 30 minutes to dry 12 T-shirts in the sun, how long does it take to dry 33 T-shirts?"
+
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {"role": "user", "content": query}
+]
+stream = client.chat.completions.create(
+  model=model,
+  messages=messages,
+  stream=True,
+  temperature=TEMP,
+  top_p=TOP_P,
+  max_tokens=MAX_TOK,
+)
+
+print("client: Start streaming chat completions...")
+printed_content = False
+
+for chunk in stream:
+  content = None
+  # Check the content is content
+  if hasattr(chunk.choices[0].delta, "content"):
+    content = chunk.choices[0].delta.content
+
+  if content is not None:
+    if not printed_content:
+        printed_content = True
+        print("\ncontent:", end="", flush=True)
+    # Extract and print the content
+    print(content, end="", flush=True)
+
+# content:<think>
+# Alright, I need to write 4 sentences where each one has at least 8 words and each subsequent sentence has one fewer word than the previous one.
+# ...
+# Final boxed answer (the four sentences):
+
+# \[
+# \boxed{
+# \begin{aligned}
+# &\text{1. The quick brown fox jumps over lazy dog and yells hello.} \\
+# &\text{2. I saw the cat on the stair with my hat.} \\
+# &\text{3. The man in the moon came down quickly today.} \\
+# &\text{4. A cat sat on the mat today patiently.}
+# \end{aligned}
+# }
+# \]
+```

SYSTEM_PROMPT.txt

@@ -0,0 +1,10 @@
+A user will ask you to solve a task. You should first draft your thinking process (inner monologue) until you have derived the final answer. Afterwards, write a self-contained summary of your thoughts (i.e. your summary should be succinct but contain all the critical steps you needed to reach the conclusion). You should use Markdown and Latex to format your response. Write both your thoughts and summary in the same language as the task posed by the user.
+
+Your thinking process must follow the template below:
+<think>
+Your thoughts or/and draft, like working through an exercise on scratch paper. Be as casual and as long as you want until you are confident to generate a correct answer.
+</think>
+
+Here, provide a concise summary that reflects your reasoning and presents a clear final answer to the user.
+
+Problem:

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": 1000000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 131072
+}

consolidated.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7804de2b5839982cac187d7cec307d8ca4a36e5dbf630eb3a4d168edcb06a603
+size 47144846024

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7638c57a327fd90243703b226a36b1ba6f780b55af821458bd5d8a7ae51335
+size 4781571736

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d82b5844cd0d5300c051cd1b3bbeb99172dac1da0d2cad352afbc4388bf1f40
+size 4781592784

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d03d76f36ed23cc0d7f27945765be2f0b7fe0beb4c1c9006818d0d61bdc931
+size 4781592800

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f6fbdd1e5ceba8f199386d99871eca3b515e56749d05c065edc0995fb8e8ae
+size 4886471600

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af37faf2f846abf0e8c8faf44d2f3fec795105bd402a2d96ec5b28a6e31b74ee
+size 4781592824

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab5aa043af28375ecee82ecdc96d590a768bbd8658a2c91df03e67482e0ff21
+size 4781592816

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947596040ad0fc5b4e032af98136e0f6ab3b038f75ac91fea1c723554e35fa76
+size 4886471600

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad31565638f4dcb3ced5af8c40cace1000a84c28535290ab8e1aee1bdd952ee5
+size 4781592824

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f613acd33ded4487bafdb0ebe01901b25ed5ae00f553f17425d591534568bbe0
+size 4781592816

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:974280a9bd4b125620130fb97ae4b50227be319d4d3978e0e4b40610dfb66d8d
+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 +1,11 @@
+{
+  "dim": 5120,
+  "n_layers": 40,
+  "head_dim": 128,
+  "hidden_dim": 32768,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "rope_theta": 1000000000.0,
+  "norm_eps": 1e-05,
+  "vocab_size": 131072
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a515798166e759a4cded03b01373dd6bf3c4e801c4e03a989169ddc09cac08
+size 19399778