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
```

Add MDPBench result

#39

by Delores-Lin - opened 24 days ago

base: refs/heads/main

←

from: refs/pr/39

Discussion Files changed

-198

Files changed (1) hide show

.eval_results/mdpbench.yaml +0 -198

.eval_results/mdpbench.yaml DELETED Viewed

@@ -1,198 +0,0 @@
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: overall
-  value: 63.9
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: digital
-  value: 80.2
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: photographed
-  value: 58.5
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: latin
-  value: 73.7
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: de
-  value: 72.4
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: en
-  value: 79.1
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: es
-  value: 65.0
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: fr
-  value: 62.1
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: id
-  value: 72.9
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: it
-  value: 82.9
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: nl
-  value: 70.2
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: pt
-  value: 83.8
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: vi
-  value: 74.9
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: non_latin
-  value: 52.8
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: ar
-  value: 64.2
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: hi
-  value: 59.0
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: jp
-  value: 50.5
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: ko
-  value: 41.6
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: ru
-  value: 54.3
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: th
-  value: 51.4
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: zh
-  value: 46.6
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin
-- dataset:
-    id: Delores-Lin/MDPBench
-    task_id: zh_t
-  value: 54.7
-  date: "2026-04-28"
-  source:
-    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
-    name: MDPBench leaderboard
-    user: Delores-Lin