Instructions to use lightonai/LightOnOCR-2-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lightonai/LightOnOCR-2-1B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="lightonai/LightOnOCR-2-1B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("lightonai/LightOnOCR-2-1B")
model = AutoModelForSeq2SeqLM.from_pretrained("lightonai/LightOnOCR-2-1B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lightonai/LightOnOCR-2-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lightonai/LightOnOCR-2-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lightonai/LightOnOCR-2-1B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/lightonai/LightOnOCR-2-1B

SGLang

How to use lightonai/LightOnOCR-2-1B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "lightonai/LightOnOCR-2-1B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lightonai/LightOnOCR-2-1B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "lightonai/LightOnOCR-2-1B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lightonai/LightOnOCR-2-1B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use lightonai/LightOnOCR-2-1B with Docker Model Runner:
```
docker model run hf.co/lightonai/LightOnOCR-2-1B
```

The exact vocab size of the model

#22

by abdullahamlwakeb - opened Jan 29

Discussion

abdullahamlwakeb

Jan 29

I have read the paper and this part of the paper suggests that the model is trained on a vocabulary less thank 151K (of the original qwe3). And this part of the paper make be more confused:

The Qwen3 decoder uses a 151,936-token multilingual vocabulary, much of which is unused for language-specific
OCR. We investigate frequency-based vocabulary pruning for English/French documents, reducing to 51k, 32k, and
16k tokens while preserving tokenizer integrity through recursive sub-token frequency propagation.
Table 4 summarizes the trade-offs. Pruning to 16k tokens reduces parameters by 13.8% with minimal OCR degradation on English benchmarks (75.4% vs 76.1% on OlmOCR-Bench). The 32k variant achieves the best speedaccuracy balance: 11.6% faster inference while retaining 96% of base performance. However, non-Latin scripts
(Arabic, Chinese) experience ∼3× token count inflation as script-specific tokens are removed. These experiments were conducted on LightOnOCR-1; we release the pruned variants as LightOnOCR-0.9B-32k-10251 andLightOnOCR-0.9B-16k-10252.

staghado

LightOn AI org Feb 9

Hi,
Vocabulary pruning was used for LightOnOCR-1 to show the tradeoffs of speed/perf depending on target languages. For v2, we simply kept the full vocabulary to support all languages.
More details in the v1 blogpost : https://huggingface.co/blog/lightonai/lightonocr#vocabulary-pruning

abdullahamlwakeb

Feb 11

Thank you so much for you awesome work @staghado

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment