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: 84.5
+  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: arxiv_math
+  value: 90.4
+  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: 80.6
+  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: table_tests
+  value: 89.9
+  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: 48.3
+  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: headers_footers
+  value: 87.6
+  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: multi_column
+  value: 85.9
+  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: 93.7
+  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: 71.4
+  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: 84.8
+  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: 57.3
+  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: 88.6
+  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: text_formatting
+  value: 64.5
+  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: 61.7
+  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 +1,224 @@
+---
+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-3-1B/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-3-1B
+
+**Same architecture as LightOnOCR-2-1B, new capabilities.** LightOnOCR-3-1B keeps the architecture of **[LightOn's](https://lighton.ai)** previous LightOnOCR-2 models, so switching requires no change, and adds the new grounding, image description and chart extraction features.
+
+## 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, handwriting, 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-3-1B shares the LightOnOCR-2 architecture and loads with the `LightOnOcr` classes available in Transformers since v5.
+
+```bash
+uv pip install transformers pillow pypdfium2
+```
+
+```python
+import torch
+from transformers import LightOnOcrForConditionalGeneration, LightOnOcrProcessor
+
+model_id = "lightonai/LightOnOCR-3-1B"
+device = "mps" if torch.backends.mps.is_available() else "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.float32 if device == "mps" else torch.bfloat16
+
+model = LightOnOcrForConditionalGeneration.from_pretrained(model_id, dtype=dtype).to(device)
+processor = LightOnOcrProcessor.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",
+)
+inputs = {k: v.to(device=device, dtype=dtype) if v.is_floating_point() else v.to(device) for k, v in inputs.items()}
+
+output_ids = model.generate(**inputs, max_new_tokens=1024)
+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-3-1B \
+    --limit-mm-per-prompt '{"image": 1}' --mm-processor-cache-gb 0 --no-enable-prefix-caching
+```
+
+```python
+import base64
+import io
+
+import pypdfium2 as pdfium
+import requests
+
+ENDPOINT = "http://localhost:8000/v1/chat/completions"
+MODEL = "lightonai/LightOnOCR-3-1B"
+PROMPT = "grounding"  # or "" for transcription-only
+
+# Render the first page of a PDF at 200 DPI (scale factor = 200/72 ≈ 2.77)
+pdf = pdfium.PdfDocument(requests.get("https://arxiv.org/pdf/2412.13663").content)
+pil_image = pdf[0].render(scale=2.77).to_pil()
+
+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 200 DPI to images using a target longest dimension of **1540px**
+* 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-3-1B&query=downloads&label=Downloads&color=blue)](https://huggingface.co/lightonai/LightOnOCR-3-1B)
+[![EU](https://img.shields.io/badge/🇪🇺%20Made%20in-Europe-blue)](https://huggingface.co/lightonai)

chat_template.jinja

@@ -0,0 +1,26 @@
+{% set image_count = namespace(value=0) %}
+{% for message in messages %}
+{% if loop.first and message['role'] != 'system' %}
+<|im_start|>system<|im_end|>
+{% endif %}
+<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}
+{{ message['content'] }}<|im_end|>
+{% 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 -%}
+<|image_pad|>
+{%- elif 'text' in content %}
+{{ content['text'] }}
+{% endif %}
+{% endfor %}
+<|im_end|>
+{% endif %}
+{% endfor %}
+{% if add_generation_prompt %}
+<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,97 @@
+{
+  "architectures": [
+    "LightOnOCRForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "image_token_id": 151655,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "pad_token_id": 151643,
+  "projector_hidden_act": "gelu",
+  "spatial_merge_size": 2,
+  "text_config": {
+    "architectures": [
+      "Qwen3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0,
+    "dtype": "bfloat16",
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 16384,
+    "max_window_layers": 28,
+    "model_type": "qwen3",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 1000000,
+      "rope_type": "default"
+    },
+    "rope_theta": 1000000,
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "tie_word_embeddings": true,
+    "vocab_size": 151936,
+    "use_qk_norm": true
+  },
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0,
+    "dtype": "bfloat16",
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 1540,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "pixtral",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "rope_parameters": {
+      "rope_theta": 10000,
+      "rope_type": "default"
+    },
+    "rope_theta": 10000
+  },
+  "vision_feature_layer": -1
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+      151645,
+      151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.2,
+  "top_k": 0,
+  "top_p": 0.9,
+  "transformers_version": "5.0.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32879861d5cdc3b2c3909d3f9a47dc8f7338685d13113c8c98c144f68b358dbb
+size 2011367464

processor_config.json

@@ -0,0 +1,43 @@
+{
+  "image_break_token": "<|vision_pad|>",
+  "image_end_token": "<|vision_end|>",
+  "image_processor": {
+    "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": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "PixtralImageProcessorFast",
+    "image_seq_length": null,
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "input_data_format": null,
+    "pad_size": null,
+    "patch_size": 14,
+    "processor_class": "PixtralProcessor",
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_tensors": null,
+    "size": {
+      "longest_edge": 1540
+    }
+  },
+  "image_token": "<|image_pad|>",
+  "patch_size": 14,
+  "processor_class": "PixtralProcessor",
+  "spatial_merge_size": 2
+}

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:f54b55fa0c3aba0c91ce09ea79ae4e62da24e2a1a630f96c4bae34aba25e234a
+size 11422822

tokenizer_config.json

@@ -0,0 +1,244 @@
+{
+  "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": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "LightOnOCRProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "image_token": "<|image_pad|>",
+  "image_break_token": "<|vision_pad|>",
+  "image_end_token": "<|vision_end|>",
+  "fix_mistral_regex": true
+}