Super-squash branch 'main' using huggingface_hub

Co-authored-by: pandora-s <[email protected]>
Co-authored-by: juliendenize <[email protected]>

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tekken.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,252 @@
+---
+library_name: vllm
+language:
+- en
+- fr
+- es
+- de
+- it
+- pt
+- nl
+- zh
+- ja
+- ko
+- ar
+license: apache-2.0
+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:
+- mistral-common
+---
+
+# Ministral 3 3B Base 2512
+The smallest model in the Ministral 3 family, **Ministral 3 3B** is a powerful, efficient tiny language model with vision capabilities.
+
+This model is the base pre-trained version, not fine-tuned for instruction or reasoning tasks, making it ideal for custom post-training processes.  
+For instruction and chat based use cases, we recommend using [Ministral 3 3B Instruct 2512](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512).
+
+The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 3B can even be deployed locally, fitting in 16GB of VRAM in BF16, and less than 8GB of RAM/VRAM when quantized.
+
+## Key Features
+Ministral 3 3B consists of two main architectural components:
+- **3.4B Language Model**
+- **0.4B Vision Encoder**
+
+The Ministral 3 3B Base model offers the following capabilities:
+- **Vision**: Enables the model to analyze images and provide insights based on visual content, in addition to text.
+- **Multilingual**: Supports dozens of languages, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, Arabic.
+- **Edge-Optimized**: Delivers best-in-class performance at a small scale, deployable anywhere.
+- **Apache 2.0 License**: Open-source license allowing usage and modification for both commercial and non-commercial purposes.
+- **Large Context Window**: Supports a 256k context window.
+
+### Use Cases
+Ideal for lightweight, real-time applications on edge or low-resource devices, such as:
+- Image captioning
+- Text classification
+- Real-time efficient translation
+- Data extraction
+- Short content generation
+- Fine-tuning and specialization
+- And more...
+  
+Bringing advanced AI capabilities to edge and distributed environments for embedded systems.
+
+## Ministral 3 Family
+
+| Model Name                     | Type               | Precision | Link                                                                                     |
+|--------------------------------|--------------------|-----------|------------------------------------------------------------------------------------------|
+| **Ministral 3 3B Base 2512**       | **Base pre-trained**   | **BF16**      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Base-2512)                |
+| Ministral 3 3B Instruct 2512   | Instruct post-trained | FP8    | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Instruct-2512)            |
+| Ministral 3 3B Reasoning 2512  | Reasoning capable  | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-3B-Reasoning-2512)           |
+| Ministral 3 8B Base 2512       | Base pre-trained   | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Base-2512)                |
+| Ministral 3 8B Instruct 2512   | Instruct post-trained | FP8    | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Instruct-2512)            |
+| Ministral 3 8B Reasoning 2512  | Reasoning capable  | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-8B-Reasoning-2512)           |
+| Ministral 3 14B Base 2512      | Base pre-trained   | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Base-2512)               |
+| Ministral 3 14B Instruct 2512  | Instruct post-trained | FP8    | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Instruct-2512)           |
+| Ministral 3 14B Reasoning 2512 | Reasoning capable  | BF16      | [Hugging Face](https://huggingface.co/mistralai/Ministral-3-14B-Reasoning-2512)          |
+
+Other formats available [here](https://huggingface.co/collections/mistralai/ministral-3-additional-checkpoints).
+
+## Benchmark Results
+
+We compare Ministral 3 to similar sized models.
+
+### Reasoning
+
+| Model                     | AIME25      | AIME24      | GPQA Diamond | LiveCodeBench |
+|---------------------------|-------------|-------------|--------------|---------------|
+| **Ministral 3 14B**       | <u>0.850</u>| <u>0.898</u>| <u>0.712</u> | <u>0.646</u>  |
+| Qwen3-14B (Thinking)      | 0.737       | 0.837       | 0.663        | 0.593         |
+|                           |             |             |              |               |
+| **Ministral 3 8B**        | 0.787       | <u>0.860</u>| 0.668        | <u>0.616</u>  |
+| Qwen3-VL-8B-Thinking      | <u>0.798</u>| <u>0.860</u>| <u>0.671</u> | 0.580         |
+|                           |             |             |              |               |
+| **Ministral 3 3B**        | <u>0.721</u>| <u>0.775</u>| 0.534        | <u>0.548</u>  |
+| Qwen3-VL-4B-Thinking      | 0.697       | 0.729       | <u>0.601</u> | 0.513         |
+
+### Instruct
+
+| Model                     | Arena Hard  | WildBench  | MATH Maj@1  | MM MTBench       |
+|---------------------------|-------------|------------|-------------|------------------|
+| **Ministral 3 14B**       | <u>0.551</u>| <u>68.5</u>| <u>0.904</u>| <u>8.49</u>      |
+| Qwen3 14B (Non-Thinking)  | 0.427       | 65.1       | 0.870       | NOT MULTIMODAL   |
+| Gemma3-12B-Instruct       | 0.436       | 63.2       | 0.854       | 6.70             |
+|                           |             |            |             |                  |
+| **Ministral 3 8B**        | 0.509       | <u>66.8</u>| 0.876       | <u>8.08</u>      |
+| Qwen3-VL-8B-Instruct      | <u>0.528</u>| 66.3       | <u>0.946</u>| 8.00             |
+|                           |             |            |             |                  |
+| **Ministral 3 3B**        | 0.305       | <u>56.8</u>| 0.830       | 7.83             |
+| Qwen3-VL-4B-Instruct      | <u>0.438</u>| <u>56.8</u>| <u>0.900</u>| <u>8.01</u>      |
+| Qwen3-VL-2B-Instruct      | 0.163       | 42.2       | 0.786       | 6.36             |
+| Gemma3-4B-Instruct        | 0.318       | 49.1       | 0.759       | 5.23             |
+
+### Base
+
+| Model               | Multilingual MMLU | MATH CoT 2-Shot | AGIEval 5-shot | MMLU Redux 5-shot | MMLU 5-shot | TriviaQA 5-shot |
+|---------------------|-------------------|-----------------|----------------|-------------------|-------------|-----------------|
+| **Ministral 3 14B** | 0.742             | <u>0.676</u>    | 0.648          | 0.820             | 0.794       | 0.749           |
+| Qwen3 14B Base      | <u>0.754</u>      | 0.620           | <u>0.661</u>   | <u>0.837</u>      | <u>0.804</u>| 0.703           |
+| Gemma 3 12B Base    | 0.690             | 0.487           | 0.587          | 0.766             | 0.745       | <u>0.788</u>    |
+|                     |                   |                 |                |                   |             |                 |
+| **Ministral 3 8B**  | <u>0.706</u>      | <u>0.626</u>    | 0.591          | 0.793             | <u>0.761</u>| <u>0.681</u>    |
+| Qwen 3 8B Base      | 0.700             | 0.576           | <u>0.596</u>   | <u>0.794</u>      | 0.760       | 0.639           |
+|                     |                   |                 |                |                   |             |                 |
+| **Ministral 3 3B**  | 0.652             | <u>0.601</u>    | 0.511          | 0.735             | 0.707       | 0.592           |
+| Qwen 3 4B Base      | <u>0.677</u>      | 0.405           | <u>0.570</u>   | <u>0.759</u>      | <u>0.713</u>| 0.530           |
+| Gemma 3 4B Base     | 0.516             | 0.294           | 0.430          | 0.626             | 0.589       | <u>0.640</u>    |
+
+## Usage
+
+The model can be used with the following frameworks;
+- [`vllm`](https://github.com/vllm-project/vllm): See [here](#vllm)
+- [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers)
+  
+### vLLM
+
+We recommend using this model with [vLLM](https://github.com/vllm-project/vllm).
+
+#### Installation
+
+Make sure to install most recent vllm:
+
+```
+uv pip install -U vllm \
+    --torch-backend=auto \
+    --extra-index-url https://wheels.vllm.ai/nightly
+```
+
+Doing so should automatically install [`mistral_common >= 1.8.6`](https://github.com/mistralai/mistral-common/releases/tag/v1.8.6).
+
+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
+
+Due to their size and the BF16 format of their weights `Ministral-3-3B-Base-2512` and `Ministral-3-8B-Base-2512` can run on a single 1xH200 GPU.
+
+A simple launch command is:
+
+```bash
+vllm serve mistralai/Ministral-3-3B-Base-2512 \
+  --tokenizer_mode mistral --config_format mistral --load_format mistral
+```
+
+Additional flags:
+
+* You can set `--max-model-len` to preserve memory. By default it is set to `262144` which is quite large but not necessary for most scenarios.
+* You can set `--max-num-batched-tokens` to balance throughput and latency, higher means higher throughput but higher latency.
+
+#### Usage of the model
+
+Here we asumme that the model `mistralai/Ministral-3-3B-Base-2512` is served and you can ping it to the domain `localhost` with the port `8000` which is the default for vLLM.
+
+<details>
+  <summary>Test Base</summary>
+
+Quick test with the base model.
+
+```python
+from openai import OpenAI
+
+# 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 = 0.15
+MAX_TOK = 256
+
+client = OpenAI(
+    api_key=openai_api_key,
+    base_url=openai_api_base,
+)
+
+models = client.models.list()
+model = models.data[0].id
+
+response = client.completions.create(
+    model=model,
+    prompt="What is the best thing in the universe ?",
+    temperature=TEMP,
+    max_tokens=MAX_TOK,
+)
+
+print(response.choices[0].text)
+```
+
+</details>
+
+### Transformers
+
+You can also use Ministral 3 3B Base 2512 with `Transformers` !
+Make sure to install `Transformers` from its first v5 release candidate or from "main":
+
+```
+pip install transformers==5.0.0rc0
+```
+
+To make the best use of our model with `Transformers` make sure to have [installed](https://github.com/mistralai/mistral-common) `mistral-common >= 1.8.6` to use our tokenizer.
+
+```bash
+pip install mistral-common --upgrade
+```
+
+Then load our tokenizer along with the model and generate:
+
+<details>
+  <summary>Python snippet</summary>
+
+```python
+from transformers import Mistral3ForConditionalGeneration, MistralCommonBackend, FineGrainedFP8Config
+
+model_id = "mistralai/Ministral-3-3B-Base-2512"
+model = Mistral3ForConditionalGeneration.from_pretrained(
+    model_id,
+    device_map="auto",
+)
+tokenizer = MistralCommonBackend.from_pretrained(model_id)
+
+input_ids = tokenizer.encode("Once about a time, France was a", return_tensors="pt")
+input_ids = input_ids.to("cuda")
+
+output = model.generate(
+    input_ids,
+    max_new_tokens=30,
+)[0]
+
+decoded_output = tokenizer.decode(output[len(input_ids[0]):])
+print(decoded_output)
+```
+
+</details>
+
+## License
+
+This model is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0.txt).
+
+*You must not use this model in a manner that infringes, misappropriates, or otherwise violates any third party’s rights, including intellectual property rights.*

config.json

@@ -0,0 +1,62 @@
+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "projector_hidden_act": "gelu",
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "max_position_embeddings": 262144,
+    "model_type": "ministral3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 26,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "beta_fast": 32.0,
+      "beta_slow": 1.0,
+      "factor": 16.0,
+      "llama_4_scaling_beta": 0.1,
+      "mscale": 1.0,
+      "mscale_all_dim": 1.0,
+      "original_max_position_embeddings": 16384,
+      "rope_theta": 1000000.0,
+      "rope_type": "yarn",
+      "type": "yarn"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "transformers_version": "5.0.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 1540,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "pixtral",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "rope_theta": 10000.0
+  },
+  "vision_feature_layer": -1
+}

consolidated.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef360c7ab1c4d3f4d4c426f6038dc2979e7e7ef4d5f016c6b23bd435f94202f8
+size 7698234952

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 262144,
+  "pad_token_id": 11,
+  "transformers_version": "5.0.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0494c0a285767920a5e469af9710b499115667f84e17c225a956a5155459249f
+size 4967581832

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd41d76f1d8e7b2fa64668d69177358dffdbd15231ccf6177798bca9de1a797
+size 2730659224

model.safetensors.index.json

@@ -0,0 +1,466 @@
+{
+  "metadata": {
+    "total_parameters": 4251743232,
+    "total_size": 7698180096
+  },
+  "weight_map": {
+    "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "multi_modal_projector.linear_1.weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.linear_2.weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.norm.weight": "model-00001-of-00002.safetensors",
+    "multi_modal_projector.patch_merger.merging_layer.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.ln_pre.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.patch_conv.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.23.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention.o_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.down_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.feed_forward.up_proj.weight": "model-00001-of-00002.safetensors",
+    "vision_tower.transformer.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

params.json

@@ -0,0 +1,47 @@
+{
+  "dim": 3072,
+  "n_layers": 26,
+  "head_dim": 128,
+  "hidden_dim": 9216,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "rope_theta": 1000000.0,
+  "norm_eps": 1e-05,
+  "vocab_size": 131072,
+  "tied_embeddings": true,
+  "max_position_embeddings": 262144,
+  "llama_4_scaling": {
+    "original_max_position_embeddings": 16384,
+    "beta": 0.1
+  },
+  "q_lora_rank": null,
+  "qk_rope_head_dim": null,
+  "qk_nope_head_dim": null,
+  "kv_lora_rank": null,
+  "v_head_dim": null,
+  "yarn": {
+    "original_max_position_embeddings": 16384,
+    "factor": 16,
+    "apply_scale": false,
+    "beta": 32,
+    "alpha": 1
+  },
+  "vision_encoder": {
+    "image_token_id": 10,
+    "intermediate_size": 4096,
+    "num_hidden_layers": 24,
+    "num_attention_heads": 16,
+    "mm_projector_id": "patch_merge",
+    "spatial_merge_size": 2,
+    "hidden_size": 1024,
+    "num_channels": 3,
+    "image_size": 1540,
+    "max_image_size": 1540,
+    "patch_size": 14,
+    "rope_theta": 10000.0,
+    "add_pre_mm_projector_layer_norm": true,
+    "adapter_bias": false,
+    "image_break_token_id": 12,
+    "image_end_token_id": 13
+  }
+}

processor_config.json

@@ -0,0 +1,42 @@
+{
+  "image_break_token": "[IMG_BREAK]",
+  "image_end_token": "[IMG_END]",
+  "image_processor": {
+    "crop_size": null,
+    "data_format": "channels_first",
+    "device": null,
+    "disable_grouping": null,
+    "do_center_crop": null,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_pad": null,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "PixtralImageProcessorFast",
+    "image_seq_length": null,
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "input_data_format": null,
+    "pad_size": null,
+    "patch_size": 14,
+    "processor_class": "PixtralProcessor",
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_tensors": null,
+    "size": {
+      "longest_edge": 1540
+    }
+  },
+  "image_token": "[IMG]",
+  "patch_size": 14,
+  "processor_class": "PixtralProcessor",
+  "spatial_merge_size": 2
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e29d19ea32eb7e26e6c0572d57cb7f9eca0f4420e0e0fe6ae1cf3be94da1c0d6
+size 16753777

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577575622324b2e099e2648be26bdeb5e5815ffe66d7004e9e3ddbf421db6bf1
+size 17078110