Instructions to use datalab-to/surya-ocr-2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use datalab-to/surya-ocr-2.5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="datalab-to/surya-ocr-2.5")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("datalab-to/surya-ocr-2.5")
model = AutoModelForMultimodalLM.from_pretrained("datalab-to/surya-ocr-2.5", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use datalab-to/surya-ocr-2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "datalab-to/surya-ocr-2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "datalab-to/surya-ocr-2.5",
		"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/datalab-to/surya-ocr-2.5

SGLang

How to use datalab-to/surya-ocr-2.5 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 "datalab-to/surya-ocr-2.5" \
    --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": "datalab-to/surya-ocr-2.5",
		"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 "datalab-to/surya-ocr-2.5" \
        --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": "datalab-to/surya-ocr-2.5",
		"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 datalab-to/surya-ocr-2.5 with Docker Model Runner:
```
docker model run hf.co/datalab-to/surya-ocr-2.5
```

hheiden commited on 8 days ago

Commit

e9915df

verified ·

1 Parent(s): a53396c

Model card: drop the MTP weights mention

Browse files

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -34,7 +34,6 @@ Surya is a 689M param OCR model with these features:
 - Multilingual - scores 74.9% on an internal benchmark set of 91 languages (more [here](#multilingual))
 - Layout analysis (table, image, header, etc.) with reading order
 - Tables as HTML, with merged cells as colspan / rowspan (row and column geometry needs a Surya 2 checkpoint; see Limitations)
-- Optional MTP weights (`datalab-to/surya-ocr-2.5-mtp`) for faster serving with vLLM
 We also ship smaller models for line-level text detection and ocr error detection.  It works on a range of documents (see [usage](#usage) and [benchmarks](#benchmarks)).
@@ -182,7 +181,7 @@ The `results.json` file contains a dict keyed by input filename (no extension).
 - Throughput is governed by the inference backend.  With `vllm`, raise `--max-num-seqs` / `--max-num-batched-tokens` (or `SURYA_INFERENCE_PARALLEL` on the client side) to keep more pages in flight. With `llama.cpp`, set `SURYA_INFERENCE_PARALLEL` to match `--parallel` on `llama-server`.
 - DPI can also impact throughput significantly - you can adjust the DPI settings to make the right throughput/accuracy tradeoff for your usecase.  Try going from 192 to 96 for improved throughput.
-- MTP can also impact latency/throughput. It is turned on automatically only when the checkpoint config declares an MTP head (the `surya-ocr-2.5-mtp` weights do; `surya-ocr-2.5` does not); set `VLLM_ENABLE_MTP=true|false` to override, and `VLLM_MTP_TOKENS` to change the draft length.
 ### From python

 - Multilingual - scores 74.9% on an internal benchmark set of 91 languages (more [here](#multilingual))
 - Layout analysis (table, image, header, etc.) with reading order
 - Tables as HTML, with merged cells as colspan / rowspan (row and column geometry needs a Surya 2 checkpoint; see Limitations)
 We also ship smaller models for line-level text detection and ocr error detection.  It works on a range of documents (see [usage](#usage) and [benchmarks](#benchmarks)).
 - Throughput is governed by the inference backend.  With `vllm`, raise `--max-num-seqs` / `--max-num-batched-tokens` (or `SURYA_INFERENCE_PARALLEL` on the client side) to keep more pages in flight. With `llama.cpp`, set `SURYA_INFERENCE_PARALLEL` to match `--parallel` on `llama-server`.
 - DPI can also impact throughput significantly - you can adjust the DPI settings to make the right throughput/accuracy tradeoff for your usecase.  Try going from 192 to 96 for improved throughput.
+- MTP can also impact latency/throughput. It is turned on automatically only when the checkpoint config declares an MTP head; set `VLLM_ENABLE_MTP=true|false` to override, and `VLLM_MTP_TOKENS` to change the draft length.
 ### From python