init

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,103 @@
+# OpenSearch-AI/Ops-ColQwen3-4B
+
+**Ops-ColQwen3-4B** is a ColPali-style multimodal embedding model based on the **Qwen3-VL-4B-Instruct** architecture, developed and open-sourced by the Alibaba Cloud OpenSearch-AI team. It maps text queries and visual documents such as images and PDF pages into a unified, aligned **multi-vector embedding space**, enabling highly effective retrieval of visual documents.
+
+The model is trained using a multi-stage strategy that combines large-scale text-based retrieval datasets with diverse visual document data. This hybrid training approach significantly enhances its capability to handle complex document understanding and retrieval tasks. On the Vidore v1–v3 benchmarks, **Ops-ColQwen3-4B** achieves **state-of-the-art results** among models of comparable size.
+
+## Key Features
+
+- **Model size**: 4 billion parameters  
+- **Multimodal alignment**: Enables fine-grained semantic alignment between text and images or PDF pages  
+- **Multi-vector embeddings**: Following the ColPali design, each input generates multiple context-aware embedding vectors; similarity is computed using **MaxSim**, enabling high-precision matching  
+- **Scalable embedding dimensions**: Supports embedding dimensions up to **2,560** during inference via an extended projection head, enabling **higher retrieval accuracy** through more expressive representations. Lower-dimensional prefixes (e.g., the first 128 or 320 dimensions) remain highly effective for lightweight applications.
+- **Multilingual support**: Covers over 30 languages  
+- **Context length**: Supports up to **32,000 tokens**  
+- **Visual token capacity**: Handles up to **1,280 visual tokens** per page input.
+
+## Usage
+
+**Requirements**
+```
+transformers>=4.57.0
+qwen-vl-utils>=0.0.14
+torch==2.8.0
+colpali_engine==0.3.12
+```
+
+**Basic Usage**
+
+```python
+from PIL import Image
+from scripts.ops_colqwen3_embedder import OpsColQwen3Embedder
+
+images = [Image.new("RGB", (32, 32), color="white"), Image.new("RGB", (16, 16), color="black")]
+
+queries = ["Is attention really all you need?", "What is the amount of bananas farmed in Salvador?"]
+
+encoder = OpsColQwen3Embedder(
+    model_name="OpenSearch-AI/Ops-Colqwen3-4B",
+    dims=320,
+    dtype=torch.float16,
+    attn_implementation="flash_attention_2",
+)
+
+query_embeddings = encoder.encode_texts(queries, batch_size=2)
+image_embeddings = encoder.encode_images(images, batch_size=2)
+
+scores = encoder.compute_scores(query_embeddings, image_embeddings)
+print(f"Scores:\n{scores}")
+```
+
+## Model Performance
+
+### Vidore v1 + v2 (NDCG@5)
+
+| Model                                      | Dim  | Vidore v1+v2 | Vidore v2 | Vidore v1 |
+|--------------------------------------------|------|--------------|-----------|-----------|
+| **Ops-ColQwen3-4B**                        | 2560 | **84.87**    | **68.7**  | **91.4**  |
+| **Ops-ColQwen3-4B**                        | 1280 | 84.71        | 68.2      | 91.3      |
+| **Ops-ColQwen3-4B**                        | 640  | 84.39        | 67.7      | 91.1      |
+| **Ops-ColQwen3-4B**                        | 320  | 84.12        | 67.0      | 91.0      |
+| **Ops-ColQwen3-4B**                        | 128  | 84.04        | 66.9      | 90.9      |
+| tomoro-colqwen3-embed-8b                   | 320  | 83.52        | 65.4      | 90.8      |
+| EvoQwen2.5-VL-Retriever-7B-v1              | 128  | 83.41        | 65.2      | 90.7      |
+| tomoro-colqwen3-embed-4b                   | 320  | 83.18        | 64.7      | 90.6      |
+| llama-nemoretriever-colembed-3b-v1         | 3072 | 83.10        | 63.3      | 91.0      |
+| SauerkrautLM-ColQwen3-8b-v0.1              | 128  | 82.91        | 62.5      | 91.1      |
+| EvoQwen2.5-VL-Retriever-3B-v1              | 128  | 82.76        | 63.0      | 90.7      |
+| SauerkrautLM-ColQwen3-4b-v0.1              | 128  | 81.97        | 59.9      | 90.8      |
+| jina-embedding-v4                          | 128  | 81.17        | 58.2      | 90.4      |
+
+
+
+### Vidore v3 (NDCG@10)
+
+| Model                                      | Dim  | PUB AVG |
+|--------------------------------------------|------|---------|
+| **Ops-ColQwen3-4B**                        | 2560 |  61.27  |
+| **Ops-ColQwen3-4B**                        | 1280 |  **61.32**  |
+| **Ops-ColQwen3-4B**                        | 640  |  61.21  |
+| **Ops-ColQwen3-4B**                        | 320  |  60.88  |
+| **Ops-ColQwen3-4B**                        | 128  |  60.23  |
+| tomoro-colqwen3-embed-4b          | 320  |  60.19  |
+| SauerkrautLM-ColQwen3-8b-v0.1              | 128  |  58.55  |
+| jina-embedding-v4                          | 128  |  57.54  |
+| llama-nemoretriever-colembed-3b-v1         | 3072 |  57.07  |
+| SauerkrautLM-ColQwen3-4b-v0.1              | 128  |  56.03  |
+
+
+> With only **128 dimensions**, `Ops-ColQwen3-4B` outperforms other 4B-parameter models such as `tomoro-colqwen3-embed-4b`, making it well-suited for latency- and memory-constrained applications.
+
+
+## Citation
+
+If you use this model in your work, please cite:
+
+```bibtex
+@misc{ops_colqwen3_4b,
+  author       = {{OpenSearch-AI}},
+  title        = {{Ops-ColQwen3: State-of-the-Art Multimodal Embedding Model for Visual Document Retrieval}},
+  year         = {2026},
+  howpublished = {\url{https://huggingface.co/OpenSearch-AI/Ops-ColQwen3-4B}},
+}
+```

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "ColQwen3VLModel"
+  ],
+  "dtype": "float32",
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

model.safetensors.index.json

@@ -0,0 +1,723 @@
+{
+  "metadata": {
+    "total_parameters": 4444371969,
+    "total_size": 8888743940
+  },
+  "weight_map": {
+    "custom_text_proj.bias": "model-00002-of-00002.safetensors",
+    "custom_text_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.norm.weight": "model-00002-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+    "visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+    "visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+    "visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "visual.pos_embed.weight": "model-00001-of-00002.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,38 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "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": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": 1310720,
+  "merge_size": 2,
+  "min_pixels": 4096,
+  "pad_size": null,
+  "patch_size": 16,
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 1310720,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2
+}

scripts/ops_colqwen3_embedder.py

@@ -0,0 +1,338 @@
+from typing import List, Union, Optional, Tuple
+import torch
+from torch import nn
+from PIL import Image
+from tqdm.auto import tqdm
+from transformers.models.qwen3_vl import Qwen3VLConfig, Qwen3VLModel, Qwen3VLProcessor
+from colpali_engine.utils.processing_utils import BaseVisualRetrieverProcessor
+from transformers import BatchEncoding, BatchFeature
+from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
+
+
+class OpsColQwen3(Qwen3VLModel):
+    """
+    OpsColQwen3 model implementation for multi-vector document retrieval.
+    """
+
+    def __init__(self, config: Qwen3VLConfig, dims: int = 320, mask_non_image_embeddings: bool = False):
+        super().__init__(config=config)
+        self.custom_text_proj = nn.Linear(self.config.text_config.hidden_size, self.config.text_config.hidden_size)
+        self.dims = dims
+        self.padding_side = "left"
+        self.mask_non_image_embeddings = mask_non_image_embeddings
+        self.post_init()
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        key_mapping = kwargs.pop("key_mapping", None)
+        if key_mapping is None:
+            key_mapping = {
+                r"^base_model\.model\.(.*)": r"\1",
+                r"^model\.(.*)": r"\1",
+            }
+
+        return super().from_pretrained(*args, **kwargs, key_mapping=key_mapping)
+
+    def forward(self, *args, **kwargs) -> torch.Tensor:
+        attention_mask = kwargs.get("attention_mask")
+        has_pixel_values = "pixel_values" in kwargs and kwargs["pixel_values"] is not None
+
+        if has_pixel_values:
+            image_grid_thw = kwargs.get("image_grid_thw")
+            if image_grid_thw is None:
+                raise ValueError("`image_grid_thw` must be provided when `pixel_values` is passed.")
+
+            if not torch.is_tensor(image_grid_thw):
+                image_grid_thw = torch.as_tensor(image_grid_thw, device=kwargs["pixel_values"].device)
+
+            offsets = image_grid_thw.prod(dim=1)
+            unpadded = [pixel_sequence[: int(offset.item())] for pixel_sequence, offset in zip(kwargs["pixel_values"], offsets)]
+
+            if unpadded:
+                kwargs["pixel_values"] = torch.cat(unpadded, dim=0)
+            else:
+                kwargs["pixel_values"] = None
+
+        kwargs.pop("return_dict", True)
+        kwargs.pop("output_hidden_states", None)
+        kwargs.pop("use_cache", None)
+
+        last_hidden_states = super().forward(*args, **kwargs, use_cache=False, output_hidden_states=True, return_dict=True).last_hidden_state
+
+        proj = self.custom_text_proj(last_hidden_states)
+        if self.dims < self.config.text_config.hidden_size:
+            proj = proj[..., : self.dims]
+        proj = proj / proj.norm(dim=-1, keepdim=True)
+
+        if attention_mask is not None:
+            proj = proj * attention_mask.unsqueeze(-1)
+
+        if has_pixel_values and self.mask_non_image_embeddings and kwargs.get("input_ids") is not None:
+            image_mask = (kwargs["input_ids"] == self.config.image_token_id).unsqueeze(-1)
+            proj = proj * image_mask
+
+        return proj
+
+    @property
+    def patch_size(self) -> int:
+        return self.visual.config.patch_size
+
+    @property
+    def spatial_merge_size(self) -> int:
+        return self.visual.config.spatial_merge_size
+
+    @property
+    def temporal_patch_size(self) -> int:
+        return getattr(self.visual.config, "temporal_patch_size", 1)
+
+
+class OpsColQwen3Processor(BaseVisualRetrieverProcessor, Qwen3VLProcessor):
+    """
+    Processor for OpsColQwen3.
+    """
+
+    query_prefix: str = "Query: "
+    visual_prompt_prefix: str = "<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>Describe the image.<|im_end|><|im_start|>assistant\n<|endoftext|>"
+    query_augmentation_token: str = "<|endoftext|>"
+    image_token: str = "<|image_pad|>"
+
+    def __init__(self, *args, **kwargs) -> None:
+        super().__init__(*args, **kwargs)
+        self.tokenizer.padding_side = "left"
+
+    @classmethod
+    def from_pretrained(cls, *args, device_map: Optional[str] = None, **kwargs):
+        instance = super().from_pretrained(*args, device_map=device_map, **kwargs)
+
+        if "max_num_visual_tokens" in kwargs:
+            instance.image_processor.max_pixels = kwargs["max_num_visual_tokens"] * 32 * 32
+            instance.image_processor.size["longest_edge"] = instance.image_processor.max_pixels
+
+        return instance
+
+    def process_images(self, images: List[Image.Image]) -> Union[BatchFeature, BatchEncoding]:
+        """Process a batch of PIL images."""
+        images = [image.convert("RGB") for image in images]
+
+        batch_doc = self.__call__(
+            text=[self.visual_prompt_prefix] * len(images),
+            images=images,
+            padding="longest",
+            return_tensors="pt",
+        )
+
+        if batch_doc["pixel_values"].numel() == 0:
+            return batch_doc
+
+        offsets = batch_doc["image_grid_thw"].prod(dim=1)
+        pixel_values = list(torch.split(batch_doc["pixel_values"], offsets.tolist()))
+        batch_doc["pixel_values"] = torch.nn.utils.rnn.pad_sequence(pixel_values, batch_first=True)
+
+        return batch_doc
+
+    def process_texts(self, texts: List[str]) -> Union[BatchFeature, BatchEncoding]:
+        """Process a list of texts."""
+        return self(text=texts, return_tensors="pt", padding="longest")
+
+    def score(
+        self,
+        qs: Union[torch.Tensor, List[torch.Tensor]],
+        ps: Union[torch.Tensor, List[torch.Tensor]],
+        device: Optional[Union[str, torch.device]] = None,
+        **kwargs,
+    ) -> torch.Tensor:
+        """Compute the MaxSim score (ColBERT-like) for query and passage embeddings."""
+        return self.score_multi_vector(qs, ps, device=device, **kwargs)
+
+    def get_n_patches(
+        self,
+        image_size: Tuple[int, int],
+        spatial_merge_size: int,
+    ) -> Tuple[int, int]:
+        """
+        Compute the number of patches (n_patches_x, n_patches_y) for an image.
+        """
+        patch_size = self.image_processor.patch_size
+        merge_size = getattr(self.image_processor, "merge_size", 1)
+
+        height_new, width_new = smart_resize(
+            width=image_size[0],
+            height=image_size[1],
+            factor=patch_size * merge_size,
+            min_pixels=self.image_processor.size["shortest_edge"],
+            max_pixels=self.image_processor.size["longest_edge"],
+        )
+
+        n_patches_x = width_new // patch_size // spatial_merge_size
+        n_patches_y = height_new // patch_size // spatial_merge_size
+
+        return n_patches_x, n_patches_y
+
+    def get_image_mask(self, batch_images: BatchFeature) -> torch.Tensor:
+        """Return a boolean tensor identifying image tokens."""
+        return batch_images.input_ids == self.image_token_id
+
+
+class OpsColQwen3Embedder:
+    """
+    Simple embedder wrapper for OpsColQwen3 model.
+
+    Args:
+        model_name: HuggingFace model name or local path
+        dims: Embedding dimension after projection
+        device: Device to run the model on
+        attn_implementation: Attention implementation
+    """
+
+    def __init__(
+        self,
+        model_name: str = "OpenSearch-AI/Ops-ColQwen3-4B",
+        dims: int = 2560,
+        device: Optional[str] = None,
+        attn_implementation: Optional[str] = None,
+        **kwargs,
+    ):
+        self.device = device or ("cuda" if torch.cuda.is_available() else "cpu")
+        self.dims = dims
+
+        if attn_implementation is None:
+            try:
+                from transformers.utils.import_utils import is_flash_attn_2_available
+
+                attn_implementation = "flash_attention_2" if is_flash_attn_2_available() else None
+            except ImportError:
+                attn_implementation = None
+
+        load_kwargs = {"dims": dims, "device_map": self.device, **kwargs}
+        if attn_implementation:
+            load_kwargs["attn_implementation"] = attn_implementation
+
+        self.model = OpsColQwen3.from_pretrained(model_name, **load_kwargs)
+        self.model.eval()
+
+        self.processor = OpsColQwen3Processor.from_pretrained(model_name)
+
+    def encode_texts(
+        self,
+        texts: List[str],
+        batch_size: int = 32,
+        show_progress: bool = False,
+    ) -> List[torch.Tensor]:
+        """
+        Encode a list of text queries.
+
+        Args:
+            texts: List of text strings to encode
+            batch_size: Batch size for processing
+            show_progress: Whether to show progress bar
+
+        Returns:
+            List of embedding tensors
+        """
+        all_embeddings = []
+
+        iterator = range(0, len(texts), batch_size)
+        if show_progress:
+            iterator = tqdm(iterator, desc="Encoding texts")
+
+        with torch.no_grad():
+            for i in iterator:
+                batch_texts = texts[i : i + batch_size]
+
+                batch_texts = [self.processor.query_prefix + t + self.processor.query_augmentation_token * 10 for t in batch_texts]
+
+                inputs = self.processor.process_texts(batch_texts)
+                inputs = {k: v.to(self.device) for k, v in inputs.items()}
+
+                embeddings = self.model(**inputs)
+                all_embeddings.extend(embeddings.cpu().to(torch.float32))
+
+        return all_embeddings
+
+    def encode_images(
+        self,
+        images: List[Union[str, Image.Image]],
+        batch_size: int = 32,
+        show_progress: bool = False,
+    ) -> List[torch.Tensor]:
+        """
+        Encode a list of images.
+
+        Args:
+            images: List of image paths or PIL Images
+            batch_size: Batch size for processing
+            show_progress: Whether to show progress bar
+
+        Returns:
+            List of embedding tensors
+        """
+        image_list = []
+        for img in images:
+            if isinstance(img, str):
+                image_list.append(Image.open(img).convert("RGB"))
+            elif isinstance(img, Image.Image):
+                image_list.append(img.convert("RGB"))
+            else:
+                raise ValueError(f"Unsupported image type: {type(img)}")
+
+        all_embeddings = []
+
+        iterator = range(0, len(image_list), batch_size)
+        if show_progress:
+            iterator = tqdm(iterator, desc="Encoding images")
+
+        with torch.no_grad():
+            for i in iterator:
+                batch_images = image_list[i : i + batch_size]
+
+                inputs = self.processor.process_images(batch_images)
+                inputs = {k: v.to(self.device) for k, v in inputs.items()}
+
+                embeddings = self.model(**inputs)
+                all_embeddings.extend(embeddings.cpu().to(torch.float32))
+
+        return all_embeddings
+
+    def compute_scores(
+        self,
+        query_embeddings: List[torch.Tensor],
+        image_embeddings: List[torch.Tensor],
+        batch_size: int = 128,
+    ) -> torch.Tensor:
+        """
+        Compute relevance scores between queries and images using MaxSim.
+
+        Args:
+            query_embeddings: List of query embedding tensors
+            image_embeddings: List of image embedding tensors
+            batch_size: Batch size for score computation
+
+        Returns:
+            Score matrix of shape (num_queries, num_images)
+        """
+        return self.processor.score_multi_vector(
+            query_embeddings,
+            image_embeddings,
+            batch_size=batch_size,
+            device=self.device,
+        )
+
+
+# Example usage
+if __name__ == "__main__":
+    images = [Image.new("RGB", (32, 32), color="white"), Image.new("RGB", (16, 16), color="black")]
+
+    queries = ["Is attention really all you need?", "What is the amount of bananas farmed in Salvador?"]
+
+    encoder = OpsColQwen3Embedder(
+        model_name="OpenSearch-AI/Ops-Colqwen3-4B",
+        dims=320,
+        dtype=torch.float16,
+        attn_implementation="flash_attention_2",
+    )
+
+    query_embeddings = encoder.encode_texts(queries, batch_size=2)
+    image_embeddings = encoder.encode_images(images, batch_size=2)
+
+    scores = encoder.compute_scores(query_embeddings, image_embeddings)
+    print(f"Scores:\n{scores}")

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_num_visual_tokens": 1280,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "ColQwen3_Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "ColQwen3_Processor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}