LightOnOCR-3 release

Co-authored-by: Bapt120 <Bapt120@users.noreply.huggingface.co>

.eval_results/olmocrbench.yaml

@@ -0,0 +1,81 @@
+- dataset:
+    id: allenai/olmOCR-bench
+    task_id: overall
+  value: 86.3
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: allenai/olmOCR-bench
+    task_id: arxiv_math
+  value: 91.1
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: allenai/olmOCR-bench
+    task_id: old_scans_math
+  value: 89.1
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: allenai/olmOCR-bench
+    task_id: table_tests
+  value: 90.2
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: allenai/olmOCR-bench
+    task_id: old_scans
+  value: 52.5
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: allenai/olmOCR-bench
+    task_id: headers_footers
+  value: 89.2
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: allenai/olmOCR-bench
+    task_id: multi_column
+  value: 85.6
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: allenai/olmOCR-bench
+    task_id: long_tiny_text
+  value: 93.2
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: allenai/olmOCR-bench
+    task_id: baseline
+  value: 99.5
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado

.eval_results/parsebench.yaml

@@ -0,0 +1,54 @@
+- dataset:
+    id: llamaindex/ParseBench
+    task_id: mean
+  value: 75.1
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: llamaindex/ParseBench
+    task_id: table
+  value: 83.8
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: llamaindex/ParseBench
+    task_id: chart
+  value: 66.1
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: llamaindex/ParseBench
+    task_id: text_content
+  value: 89.9
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: llamaindex/ParseBench
+    task_id: text_formatting
+  value: 67.6
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado
+- dataset:
+    id: llamaindex/ParseBench
+    task_id: layout
+  value: 68.3
+  date: '2026-10-08'
+  source:
+    url: https://huggingface.co/blog/lightonai/lightonocr-3
+    name: LightOnOCR-3 results
+    user: staghado

.gitattributes

@@ -0,0 +1,37 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+lightonocr3_logo.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,223 @@
+---
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
+tags:
+- ocr
+- document-understanding
+- visual-grounding
+- vision-language
+- tables
+- forms
+---
+
+<div align="center">
+
+<img src="https://huggingface.co/lightonai/LightOnOCR-3-4B/resolve/main/lightonocr3_logo.png" alt="LightOnOCR-3 logo" width="600">
+
+[![Website](https://img.shields.io/badge/LightOn-Website-blue?logo=google-chrome)](https://lighton.ai)
+[![LinkedIn](https://img.shields.io/badge/LightOn-LinkedIn-0A66C2?logo=linkedin)](https://www.linkedin.com/company/lighton/)
+[![X](https://img.shields.io/badge/@LightOnIO-X-black?logo=x)](https://x.com/LightOnIO)
+
+📄 [Paper](https://arxiv.org/pdf/2601.14251) | 📝 [Blog](https://huggingface.co/blog/lightonai/lightonocr-3) | 🚀 [Demo](https://huggingface.co/spaces/lightonai/LightOnOCR-3-Demo) | 💻 [GitHub](https://github.com/lightonai/LightOnOCR) | 🤗 [LightOnOCR-2-1B](https://huggingface.co/lightonai/LightOnOCR-2-1B)
+
+</div>
+
+# LightOnOCR-3-4B
+
+**Best OCR model.** LightOnOCR-3-4B is the largest and most accurate model of the LightOnOCR-3 family, **[LightOn's](https://lighton.ai)** new generation of lightweight end-to-end OCR models with layout and visual understanding. We recommend it for most OCR tasks.
+
+## About LightOnOCR-3
+
+LightOnOCR-3 is a new family of highly performant lightweight OCR models. Compared to the previous generation, they bring significant improvements in speed and transcription quality and introduce new visual understanding features: the models now output bounding box coordinates with labels for all visual elements of a document, short descriptions of images, and the numerical data of figures and charts. With these capabilities, they offer a ready-to-use, easier-to-maintain alternative to complex document understanding pipelines.
+
+The models come in three sizes. The 1B keeps the LightOnOCR-2-1B architecture, while the 0.8B and 4B adopt the Qwen3.5 vision-language architecture, which simplifies integration with existing tools and brings a significant speed-up. All models are released under the Apache 2.0 license for research and commercial use.
+
+## Highlights
+
+* 📝 **Transcription mode:** call the model with an empty prompt and get the full page text, as before. Switching from LightOnOCR-2 requires no change
+* 📍 **Grounding mode:** call it with the `grounding` prompt and every block comes back with a label and a bounding box
+* 🖼️ **Visual understanding:** images get a short description, charts become a table of their data points
+* 🧠 **End-to-End:** one model instead of a document understanding pipeline, easier to deploy and maintain
+* 🧾 **Versatile:** handles tables, receipts, forms, charts, multi-column layouts, and math notation
+
+---
+
+## Model Variants
+
+| Variant | Description |
+|---------|-------------|
+| **[LightOnOCR-3-4B](https://huggingface.co/lightonai/LightOnOCR-3-4B)** | Best OCR model, recommended for most tasks |
+| **[LightOnOCR-3-1B](https://huggingface.co/lightonai/LightOnOCR-3-1B)** | LightOnOCR-2 architecture, drop-in upgrade for existing deployments |
+| **[LightOnOCR-3-0.8B](https://huggingface.co/lightonai/LightOnOCR-3-0.8B)** | Fast and Efficient model |
+
+---
+
+## Prompt Modes
+
+The models can be used as before in a **transcription-only mode**: called with an empty prompt (`""`; the image only), they output all textual elements of the page as markdown. If you are currently using our previous models, switching to LightOnOCR-3 requires no change, as this is the default behavior.
+
+The new usage mode is to call the models with the `grounding` prompt. They then output the new vision features alongside the transcribed text. Each block of content is prepended with a placeholder giving its type and its bounding box, in page coordinates normalized to 0–1000:
+
+```
+![title](80,70,920,140)
+# Company report 2025
+
+![text](80,175,920,225)
+Revenue rose 20%.
+
+![image](80,285,460,545)
+A solar-powered factory.
+
+![chart](540,285,920,545)
+<table>
+  <tr><th>Year</th><th>Revenue</th></tr>
+  <tr><td>2024</td><td>€10M</td></tr>
+  <tr><td>2025</td><td>€12M</td></tr>
+</table>
+```
+
+* **Text blocks** contain the transcribed content of paragraphs, titles and other text elements.
+* **Image blocks** pair a bounding box with a short description, making visual content accessible to retrieval and question-answering pipelines.
+* **Chart blocks** contain an HTML table of the data points extracted from the figure, turning visual information into structured data.
+
+The placeholder label is one of:
+
+| Label | Definition |
+|---|---|
+| `text` | Ordinary body text and paragraphs. |
+| `title` | Document, section, or paragraph headings. |
+| `list` | Bulleted or numbered-list content. |
+| `header` | Text in the page header. |
+| `footer` | Text in the page footer. |
+| `page_number` | Page-number regions. |
+| `footnote` | Footnote text. |
+| `caption` | Captions associated with figures, tables, or other visual elements. |
+| `formula` | Mathematical formulas and equations. |
+| `code` | Code blocks or code-like text. |
+| `table` | Table regions and their content. |
+| `image` | Illustrations, photographs, and other image regions. |
+| `chart` | Charts, graphs, and plotted visual data. |
+| `header_image` | Image regions in page headers, such as logos. |
+| `footer_image` | Image regions in page footers. |
+| `aside_text` | Marginal or side text outside the main text flow. |
+| `+` suffix | Marks a continuation block, not a separate semantic class. |
+
+Grounding adds about 25% output tokens over plain transcription (1,433 vs 1,158 tokens per page on average for the 4B). Other instructions are out of distribution: use the empty prompt (`""`) or `grounding`.
+
+---
+
+## Usage with Transformers
+
+> **Note:** LightOnOCR-3-4B loads with the Qwen3.5 classes (Transformers ≥ 5.2, saved with 5.5.4). It is trained and evaluated with thinking disabled, which is the chat template default.
+
+```bash
+uv pip install "transformers>=5.5.4" pillow pypdfium2
+```
+
+```python
+import torch
+from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
+
+model_id = "lightonai/LightOnOCR-3-4B"
+model = Qwen3_5ForConditionalGeneration.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")
+processor = AutoProcessor.from_pretrained(model_id)
+
+url = "https://huggingface.co/datasets/hf-internal-testing/fixtures_ocr/resolve/main/SROIE-receipt.jpeg"
+prompt = "grounding"  # or "" for transcription-only
+
+content = [{"type": "image", "url": url}]
+if prompt:
+    content.append({"type": "text", "text": prompt})
+conversation = [{"role": "user", "content": content}]
+
+inputs = processor.apply_chat_template(
+    conversation,
+    add_generation_prompt=True,
+    tokenize=True,
+    return_dict=True,
+    return_tensors="pt",
+    enable_thinking=False,
+).to(model.device)
+
+output_ids = model.generate(**inputs, max_new_tokens=1024, do_sample=True, temperature=0.2)
+generated_ids = output_ids[0, inputs["input_ids"].shape[1]:]
+print(processor.decode(generated_ids, skip_special_tokens=True))
+```
+
+---
+
+## Usage with vLLM
+
+```bash
+vllm serve lightonai/LightOnOCR-3-4B \
+  --trust-remote-code \
+  --default-chat-template-kwargs '{"enable_thinking": false}'
+```
+
+```python
+import base64
+import io
+
+import pypdfium2 as pdfium
+import requests
+
+ENDPOINT = "http://localhost:8000/v1/chat/completions"
+MODEL = "lightonai/LightOnOCR-3-4B"
+PROMPT = "grounding"  # or "" for transcription-only
+
+# Render the first page of a PDF at 400 DPI, then resize to a longest edge of 2048 px (aspect ratio preserved)
+pdf = pdfium.PdfDocument(requests.get("https://arxiv.org/pdf/2412.13663").content)
+pil_image = pdf[0].render(scale=400 / 72).to_pil()
+pil_image.thumbnail((2048, 2048))
+
+buffer = io.BytesIO()
+pil_image.save(buffer, format="PNG")
+image_base64 = base64.b64encode(buffer.getvalue()).decode("utf-8")
+
+content = [{"type": "image_url", "image_url": {"url": f"data:image/png;base64,{image_base64}"}}]
+if PROMPT:
+    content.append({"type": "text", "text": PROMPT})
+
+payload = {
+    "model": MODEL,
+    "messages": [{"role": "user", "content": content}],
+    "max_tokens": 4096,
+    "temperature": 0.2,
+    "top_p": 0.9,
+}
+
+response = requests.post(ENDPOINT, json=payload)
+print(response.json()["choices"][0]["message"]["content"])
+```
+
+The [LightOnOCR repository](https://github.com/lightonai/LightOnOCR) on GitHub provides a minimal client, CLI and viewer for the models served with vLLM, plus the code to reproduce our benchmarks.
+
+---
+
+## Rendering and Preprocessing Tips
+
+* Render PDFs at 400 DPI to images using a target longest dimension of **2048px**
+* Maintain aspect ratio to preserve text geometry
+
+---
+
+## License
+
+Apache License 2.0
+
+---
+
+## Citation
+
+```bibtex
+@misc{lightonocr2_2026,
+  title        = {LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR},
+  author       = {Said Taghadouini and Adrien Cavaill\`{e}s and Baptiste Aubertin},
+  year         = {2026},
+  howpublished = {\url{https://arxiv.org/abs/2601.14251}}
+}
+```
+
+[![Downloads](https://img.shields.io/badge/dynamic/json?url=https://huggingface.co/api/models/lightonai/LightOnOCR-3-4B&query=downloads&label=Downloads&color=blue)](https://huggingface.co/lightonai/LightOnOCR-3-4B)
+[![EU](https://img.shields.io/badge/🇪🇺%20Made%20in-Europe-blue)](https://huggingface.co/lightonai)

README.no_thinking.md

@@ -0,0 +1,11 @@
+# Serving default
+
+The bundled `chat_template.jinja` defaults to `enable_thinking=false` when the
+caller omits the chat-template kwarg. Serving code should still pass the
+explicit vLLM flag for clarity:
+
+```bash
+--default-chat-template-kwargs '{"enable_thinking": false}'
+```
+
+Passing `enable_thinking=true` explicitly remains an opt-in override.

chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is not defined or enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 0,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.4",
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "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_5",
+    "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": 248054,
+  "vision_start_token_id": 248053
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 248046,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 248044,
+  "transformers_version": "5.5.4",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b0dab74a2dab02d5b10ca56322255024ed8dca35c02746b42e9f296aaeb4e67
+size 9078620536

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+    "size": {
+        "longest_edge": 16777216,
+        "shortest_edge": 65536
+    },
+    "patch_size": 16,
+    "temporal_patch_size": 2,
+    "merge_size": 2,
+    "image_mean": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "image_std": [
+        0.5,
+        0.5,
+        0.5
+    ],
+    "processor_class": "Qwen3VLProcessor",
+    "image_processor_type": "Qwen2VLImageProcessorFast"
+}

processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "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
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}