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
```

add AIBOM

#12

by fatima113 - opened Jun 13, 2025

base: refs/heads/main

←

from: refs/pr/12

Discussion Files changed

+111

-0

Files changed (1) hide show

reducto_RolmOCR.json +111 -0

reducto_RolmOCR.json ADDED Viewed

	@@ -0,0 +1,111 @@

+{
+    "bomFormat": "CycloneDX",
+    "specVersion": "1.6",
+    "serialNumber": "urn:uuid:d8411c65-830d-47b0-928a-db17d1885512",
+    "version": 1,
+    "metadata": {
+        "timestamp": "2025-06-05T09:41:39.920661+00:00",
+        "component": {
+            "type": "machine-learning-model",
+            "bom-ref": "reducto/RolmOCR-9488b32d-f36e-501e-bed2-4e214df3640f",
+            "name": "reducto/RolmOCR",
+            "externalReferences": [
+                {
+                    "url": "https://huggingface.co/reducto/RolmOCR",
+                    "type": "documentation"
+                }
+            ],
+            "modelCard": {
+                "modelParameters": {
+                    "task": "image-text-to-text",
+                    "architectureFamily": "qwen2_5_vl",
+                    "modelArchitecture": "Qwen2_5_VLForConditionalGeneration",
+                    "datasets": [
+                        {
+                            "ref": "allenai/olmOCR-mix-0225-60ff9e3d-6392-58a9-97f8-ebf183f689d7"
+                        }
+                    ]
+                },
+                "properties": [
+                    {
+                        "name": "library_name",
+                        "value": "transformers"
+                    },
+                    {
+                        "name": "base_model",
+                        "value": "Qwen/Qwen2.5-VL-7B-Instruct"
+                    }
+                ]
+            },
+            "authors": [
+                {
+                    "name": "reducto"
+                }
+            ],
+            "licenses": [
+                {
+                    "license": {
+                        "id": "Apache-2.0",
+                        "url": "https://spdx.org/licenses/Apache-2.0.html"
+                    }
+                }
+            ],
+            "tags": [
+                "transformers",
+                "safetensors",
+                "qwen2_5_vl",
+                "image-text-to-text",
+                "conversational",
+                "dataset:allenai/olmOCR-mix-0225",
+                "base_model:Qwen/Qwen2.5-VL-7B-Instruct",
+                "base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct",
+                "license:apache-2.0",
+                "text-generation-inference",
+                "endpoints_compatible",
+                "region:us"
+            ]
+        }
+    },
+    "components": [
+        {
+            "type": "data",
+            "bom-ref": "allenai/olmOCR-mix-0225-60ff9e3d-6392-58a9-97f8-ebf183f689d7",
+            "name": "allenai/olmOCR-mix-0225",
+            "data": [
+                {
+                    "type": "dataset",
+                    "bom-ref": "allenai/olmOCR-mix-0225-60ff9e3d-6392-58a9-97f8-ebf183f689d7",
+                    "name": "allenai/olmOCR-mix-0225",
+                    "contents": {
+                        "url": "https://huggingface.co/datasets/allenai/olmOCR-mix-0225",
+                        "properties": [
+                            {
+                                "name": "configs",
+                                "value": "Name of the dataset subset: 00_documents {\"split\": \"train_s2pdf\", \"path\": [\"train-s2pdf.parquet\"]}, {\"split\": \"eval_s2pdf\", \"path\": [\"eval-s2pdf.parquet\"]}"
+                            },
+                            {
+                                "name": "configs",
+                                "value": "Name of the dataset subset: 01_books {\"split\": \"train_iabooks\", \"path\": [\"train-iabooks.parquet\"]}, {\"split\": \"eval_iabooks\", \"path\": [\"eval-iabooks.parquet\"]}"
+                            },
+                            {
+                                "name": "license",
+                                "value": "odc-by"
+                            }
+                        ]
+                    },
+                    "governance": {
+                        "owners": [
+                            {
+                                "organization": {
+                                    "name": "allenai",
+                                    "url": "https://huggingface.co/allenai"
+                                }
+                            }
+                        ]
+                    },
+                    "description": "\n\t\n\t\t\n\t\tolmOCR-mix-0225\n\t\n\nolmOCR-mix-0225 is a dataset of ~250,000 PDF pages which have been OCRed into plain-text in a natural reading order using gpt-4o-2024-08-06 and a special\nprompting strategy that preserves any born-digital content from each page.\nThis dataset can be used to train, fine-tune, or evaluate your own OCR document pipeline.\nQuick links:\n\n\ud83d\udcc3 Paper\n\ud83e\udd17 Model\n\ud83d\udee0\ufe0f Code\n\ud83c\udfae Demo\n\n\n\t\n\t\t\n\t\n\t\n\t\tData Mix\n\t\n\n\n\t\n\t\n\t\n\t\tTable 1: Training set composition by source\n\t\n\n\n\t\n\t\t\nSource\nUnique\u2026 See the full description on the dataset page: https://huggingface.co/datasets/allenai/olmOCR-mix-0225."
+                }
+            ]
+        }
+    ]
+}