Upload LightOnOCR-2-1B model

.gitattributes

@@ -33,3 +33,6 @@ 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
+benchmark.png filter=lfs diff=lfs merge=lfs -text
+lightonocr-banner.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+license: apache-2.0
+pipeline_tag: image-text-to-text
+language:
+- en
+- fr
+- de
+- es
+- it
+- nl
+- pt
+- sv
+- da
+- zh
+- ja
+library_name: transformers
+tags:
+- ocr
+- document-understanding
+- vision-language
+- pdf
+- tables
+- forms
+---
+
+<div align="center">
+  <img src="lightonocr-banner.png" alt="LightOnOCR-2-1B Banner" width="600"/>
+</div>
+
+# LightOnOCR-2-1B
+
+**Best OCR model .** LightOnOCR-2-1B is our flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks.
+
+## About LightOnOCR-2
+
+LightOnOCR-2 is an efficient end-to-end 1B-parameter vision-language model for converting documents (PDFs, scans, images) into clean, naturally ordered text without relying on brittle pipelines. This second version is trained on a larger and higher-quality corpus with stronger French, arXiv, and scan coverage, improved LaTeX handling, and cleaner normalization. LightOnOCR-2 achieves state-of-the-art performance on OlmOCR-Bench while being ~9× smaller and significantly faster than competing approaches.
+
+## Highlights
+
+* ⚡ **Speed:** 3.3× faster than Chandra OCR, 1.7× faster than OlmOCR, 5× faster than dots.ocr, 2× faster than PaddleOCR-VL-0.9B, 1.73× faster than DeepSeekOCR
+* 💸 **Efficiency:** Processes 5.71 pages/s on a single H100 (~493k pages/day) for **<$0.01 per 1,000 pages**
+* 🧠 **End-to-End:** Fully differentiable, no external OCR pipeline
+* 🧾 **Versatile:** Handles tables, receipts, forms, multi-column layouts, and math notation
+* 📍 **Image detection:** Predicts bounding boxes for embedded images (bbox variants)
+
+---
+
+📄 **[Paper]( https://arxiv.org/pdf/2601.14251)** | 📝 **[Blog Post](https://huggingface.co/blog/lightonai/lightonocr-2)** | 🚀 **[Demo](https://huggingface.co/spaces/lightonai/LightOnOCR-2-1B-Demo)** | 📊 **[Dataset](https://huggingface.co/datasets/lightonai/LightOnOCR-mix-0126)** | 📊 **[BBox Dataset](https://huggingface.co/datasets/lightonai/LightOnOCR-bbox-mix-0126)** | 📓 **[Finetuning Notebook](https://colab.research.google.com/drive/1WjbsFJZ4vOAAlKtcCauFLn_evo5UBRNa?usp=sharing)**
+
+---
+
+## Model Variants
+
+| Variant | Description |
+|---------|-------------|
+| **[LightOnOCR-2-1B](https://huggingface.co/lightonai/LightOnOCR-2-1B)** | Best OCR model  |
+| **[LightOnOCR-2-1B-base](https://huggingface.co/lightonai/LightOnOCR-2-1B-base)** | Base model, ideal for fine-tuning |
+| **[LightOnOCR-2-1B-bbox](https://huggingface.co/lightonai/LightOnOCR-2-1B-bbox)** | Best model with image bounding boxes |
+| **[LightOnOCR-2-1B-bbox-base](https://huggingface.co/lightonai/LightOnOCR-2-1B-bbox-base)** | Base bbox model, ideal for fine-tuning |
+| **[LightOnOCR-2-1B-ocr-soup](https://huggingface.co/lightonai/LightOnOCR-2-1B-ocr-soup)** | Merged variant for extra robustness |
+| **[LightOnOCR-2-1B-bbox-soup](https://huggingface.co/lightonai/LightOnOCR-2-1B-bbox-soup)** | Merged variant: OCR + bbox combined |
+
+---
+
+## Benchmarks
+
+<div align="center">
+  <img src="benchmark.png" alt="OlmOCR-Bench Results" width="900"/>
+</div>
+
+*See the [paper](https://arxiv.org/pdf/2601.14251) for full benchmark details and methodology.*
+
+---
+
+## Usage with Transformers
+
+> **Note:** LightOnOCR-2 is avaible in latest transformers release starting from v5.
+
+```bash
+uv pip install transformers # => 5.0.0
+uv pip install pillow pypdfium2
+```
+
+```python
+import torch
+from transformers import LightOnOcrForConditionalGeneration, LightOnOcrProcessor
+
+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("lightonai/LightOnOCR-2-1B", torch_dtype=dtype).to(device)
+processor = LightOnOcrProcessor.from_pretrained("lightonai/LightOnOCR-2-1B")
+
+url = "https://huggingface.co/datasets/hf-internal-testing/fixtures_ocr/resolve/main/SROIE-receipt.jpeg"
+
+conversation = [{"role": "user", "content": [{"type": "image", "url": url}]}]
+
+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]:]
+output_text = processor.decode(generated_ids, skip_special_tokens=True)
+print(output_text)
+```
+
+---
+
+## Usage with vLLM
+
+```bash
+vllm serve lightonai/LightOnOCR-2-1B \
+    --limit-mm-per-prompt '{"image": 1}' --mm-processor-cache-gb 0 --no-enable-prefix-caching
+```
+
+```python
+import base64
+import requests
+import pypdfium2 as pdfium
+import io
+
+ENDPOINT = "http://localhost:8000/v1/chat/completions"
+MODEL = "lightonai/LightOnOCR-2-1B"
+
+# Download PDF from arXiv
+pdf_url = "https://arxiv.org/pdf/2412.13663"
+pdf_data = requests.get(pdf_url).content
+
+# Open PDF and convert first page to image
+pdf = pdfium.PdfDocument(pdf_data)
+page = pdf[0]
+# Render at 200 DPI (scale factor = 200/72 ≈ 2.77)
+pil_image = page.render(scale=2.77).to_pil()
+
+# Convert to base64
+buffer = io.BytesIO()
+pil_image.save(buffer, format="PNG")
+image_base64 = base64.b64encode(buffer.getvalue()).decode('utf-8')
+
+# Make request
+payload = {
+    "model": MODEL,
+    "messages": [{
+        "role": "user",
+        "content": [{
+            "type": "image_url",
+            "image_url": {"url": f"data:image/png;base64,{image_base64}"}
+        }]
+    }],
+    "max_tokens": 4096,
+    "temperature": 0.2,
+    "top_p": 0.9,
+}
+
+response = requests.post(ENDPOINT, json=payload)
+text = response.json()['choices'][0]['message']['content']
+print(text)
+```
+
+---
+
+## 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
+
+---
+
+## Fine-tuning
+
+LightOnOCR-2 is fully differentiable and supports:
+
+* LoRA fine-tuning
+* Domain adaptation (receipts, scientific articles, forms, etc.)
+* Multilingual fine-tuning with task-specific corpora
+
+For fine-tuning, we recommend starting with the **[LightOnOCR-2-1B-base](https://huggingface.co/lightonai/LightOnOCR-2-1B-base)** variant.
+
+---
+
+## 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/pdf/2601.14251}}
+}
+```

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 +1,26 @@
+{% 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:cbe12d0831cca119facce91268fc7c5fb72babdf919a6e352e3131bda85c8fbb
+size 2011367489

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,
+  "fix_mistral_regex": true,
+  "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|>"
+}