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
```

"model_type": "lighton_ocr"

by KoichiYasuoka - opened Jan 20

base: refs/heads/main

←

from: refs/pr/7

Discussion Files changed

-1

KoichiYasuoka

Jan 20

"model_type" is not "mistral3"

"model_type": "lighton_ocr"0ef35500

Xiakj

Jan 21

ValueError: The checkpoint you are trying to load has model type lighton_ocr
but Transformers does not recognize this architecture.

KoichiYasuoka

Jan 21

"lighton_ocr" is now supported by transformers==5.0.0rc3

Xiakj

Jan 21

This comment has been hidden (marked as Spam)

Xiakj

Jan 21

"lighton_ocr" is now supported by transformers==5.0.0rc3

still error:

(APIServer pid=56139) File "/mnt/work/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/multimodal/registry.py", line 261, in _create_processing_info
(APIServer pid=56139) return factories.info(ctx)
(APIServer pid=56139) ^^^^^^^^^^^^^^^^^^^
(APIServer pid=56139) File "/mnt/work/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/model_executor/models/mistral3.py", line 342, in _build_mistral3_info
(APIServer pid=56139) hf_config = ctx.get_hf_config(Mistral3Config)
(APIServer pid=56139) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(APIServer pid=56139) File "/mnt/work/miniconda3/envs/vllm/lib/python3.11/site-packages/vllm/multimodal/processing.py", line 1132, in get_hf_config
(APIServer pid=56139) raise TypeError(
(APIServer pid=56139) TypeError: Invalid type of HuggingFace config. Expected type: <class 'transformers.models.mistral3.configuration_mistral3.Mistral3Config'>, but found type: <class 'transformers.models.lighton_ocr.configuration_lighton_ocr.LightOnOcrConfig'>
(vllm) admin@8-n01:/mnt/work/xiakj/hf$ pip list|grep transformers
transformers 5.0.0rc3
(vllm) admin@8-n01:/mnt/work/xiakj/hf$ vi LightOnOCR-2-1B/config.json
(vllm) admin@8-n01:/mnt/work/xiakj/hf$ cat LightOnOCR-2-1B/config.json |grep lighton_ocr
"model_type": "lighton_ocr",
(vllm) admin@8-n01:/mnt/work/xiakj/hf$ cat LightOnOCR-2-1B/config.json
{
"architectures": [
"LightOnOCRForConditionalGeneration"
],
"dtype": "bfloat16",
"eos_token_id": 151645,
"image_token_id": 151655,
"model_type": "lighton_ocr",
"multimodal_projector_bias": false,

KoichiYasuoka

Jan 21

Oh... vLLM doesn't catch up transformers==5.0.0rc3 yet. And I've just found another bug on transformers==5.0.0rc3 . Sorry but it is too early for us to change "model_type" into "lighton_ocr" and I will wait for official release of transformers 5.0.0 and vLLM.

KoichiYasuoka changed pull request status to closed Jan 21

Xiakj

Jan 21

Oh... vLLM doesn't catch up transformers==5.0.0rc3 yet. And I've just found another bug on transformers==5.0.0rc3 . Sorry but it is too early for us to change "model_type" into "lighton_ocr" and I will wait for official release of transformers 5.0.0 and vLLM.

okk.

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