Instructions to use reducto/RolmOCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use reducto/RolmOCR with Transformers:

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

pipe = pipeline("image-text-to-text", model="reducto/RolmOCR")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("reducto/RolmOCR")
model = AutoModelForImageTextToText.from_pretrained("reducto/RolmOCR")
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 reducto/RolmOCR with vLLM:

Install from pip and serve model

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

SGLang

How to use reducto/RolmOCR 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 "reducto/RolmOCR" \
    --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": "reducto/RolmOCR",
		"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 "reducto/RolmOCR" \
        --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": "reducto/RolmOCR",
		"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 reducto/RolmOCR with Docker Model Runner:
```
docker model run hf.co/reducto/RolmOCR
```

i got this error

by Nethriya - opened Apr 7, 2025

Discussion

Nethriya

Apr 7, 2025

NameError Traceback (most recent call last)
Cell In[84], line 4
1 from transformers import AutoProcessor, AutoModelForImageTextToText
3 processor = AutoProcessor.from_pretrained("reducto/RolmOCR")
----> 4 model = AutoModelForImageTextToText.from_pretrained("reducto/RolmOCR")

File /opt/pytorch/lib/python3.12/site-packages/transformers/models/auto/auto_factory.py:571, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
569 if model_class.config_class == config.sub_configs.get("text_config", None):
570 config = config.get_text_config()
--> 571 return model_class.from_pretrained(
572 pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
573 )
574 raise ValueError(
575 f"Unrecognized configuration class {config.class} for this kind of AutoModel: {cls.name}.\n"
576 f"Model type should be one of {', '.join(c.name for c in cls._model_mapping.keys())}."
577 )

File /opt/pytorch/lib/python3.12/site-packages/transformers/modeling_utils.py:279, in restore_default_torch_dtype.._wrapper(*args, **kwargs)
277 old_dtype = torch.get_default_dtype()
278 try:
--> 279 return func(*args, **kwargs)
280 finally:
281 torch.set_default_dtype(old_dtype)

File /opt/pytorch/lib/python3.12/site-packages/transformers/modeling_utils.py:4333, in PreTrainedModel.from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, weights_only, *model_args, **kwargs)
4330 config.name_or_path = pretrained_model_name_or_path
4332 # Instantiate model.
-> 4333 model_init_context = cls.get_init_context(is_quantized, _is_ds_init_called)
4335 config = copy.deepcopy(config) # We do not want to modify the config inplace in from_pretrained.
4336 if not getattr(config, "_attn_implementation_autoset", False):

File /opt/pytorch/lib/python3.12/site-packages/transformers/modeling_utils.py:3736, in PreTrainedModel.get_init_context(cls, is_quantized, _is_ds_init_called)
3734 init_contexts.append(set_quantized_state())
3735 else:
-> 3736 init_contexts = [no_init_weights(), init_empty_weights()]
3738 return init_contexts

NameError: name 'init_empty_weights' is not defined

KimChen

Apr 7, 2025

@Nethriya This issue is from transformers issue

It will be fix soon.

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