Instructions to use MuseMesh/sansar-ocr-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MuseMesh/sansar-ocr-2b with Transformers:

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

pipe = pipeline("image-text-to-text", model="MuseMesh/sansar-ocr-2b")
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("MuseMesh/sansar-ocr-2b")
model = AutoModelForMultimodalLM.from_pretrained("MuseMesh/sansar-ocr-2b", 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 MuseMesh/sansar-ocr-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MuseMesh/sansar-ocr-2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MuseMesh/sansar-ocr-2b",
		"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/MuseMesh/sansar-ocr-2b

SGLang

How to use MuseMesh/sansar-ocr-2b 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 "MuseMesh/sansar-ocr-2b" \
    --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": "MuseMesh/sansar-ocr-2b",
		"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 "MuseMesh/sansar-ocr-2b" \
        --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": "MuseMesh/sansar-ocr-2b",
		"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 MuseMesh/sansar-ocr-2b with Docker Model Runner:
```
docker model run hf.co/MuseMesh/sansar-ocr-2b
```

sansar-ocr-2b

File size: 2,512 Bytes

83299c4

{
 "check": "median letter CER of the staged weights on the 54 bench_v1 test pages (score_pages.py via report_eval.py) within 0.003 of the recorded HF cross-check",
 "passed": true,
 "staged_dir": "/run/media/kushal/Kush/sansar/release/hf/sansar-ocr-2b-clean/v0.1.0",
 "engine": "transformers generate, release ocr_page.py + release generation_config (greedy)",
 "result": {
  "n": 54,
  "missing": [],
  "cer_letters": {
   "n": 54,
   "median": 0.0105,
   "mean": 0.0231
  },
  "cer": {
   "n": 54,
   "median": 0.035,
   "mean": 0.0476
  },
  "groups": {
   "footnotes:no": {
    "n": 49,
    "median": 0.0097,
    "mean": 0.0228
   },
   "footnotes:yes": {
    "n": 5,
    "median": 0.02,
    "mean": 0.0253
   },
   "header:no": {
    "n": 23,
    "median": 0.0097,
    "mean": 0.023
   },
   "header:yes": {
    "n": 31,
    "median": 0.0112,
    "mean": 0.0231
   },
   "old_ocr_cer:high": {
    "n": 18,
    "median": 0.0314,
    "mean": 0.0453
   },
   "old_ocr_cer:low": {
    "n": 18,
    "median": 0.007,
    "mean": 0.0129
   },
   "old_ocr_cer:mid": {
    "n": 18,
    "median": 0.0072,
    "mean": 0.011
   },
   "tier:kept": {
    "n": 39,
    "median": 0.0078,
    "mean": 0.0234
   },
   "tier:mid": {
    "n": 15,
    "median": 0.0131,
    "mean": 0.0221
   }
  },
  "better_than_google_vision_pages": 38
 },
 "compared_to": {
  "OCR-VLM v1.2-clean (HF)": {
   "recorded_median": 0.0106,
   "recorded_mean": 0.0229,
   "pages_identical_cer": 41,
   "pages_compared": 54,
   "max_page_abs_diff": 0.004,
   "median_page_abs_diff": 0.0
  },
  "OCR-VLM v1.2-clean (vLLM)": {
   "recorded_median": 0.0106,
   "recorded_mean": 0.0227,
   "pages_identical_cer": 39,
   "pages_compared": 54,
   "max_page_abs_diff": 0.0203,
   "median_page_abs_diff": 0.0
  }
 },
 "rescored_run_transcriptions": {
  "run transcriptions, vLLM A100 (re-scored)": {
   "n": 54,
   "cer_letters": {
    "n": 54,
    "median": 0.0106,
    "mean": 0.0227
   },
   "cer": {
    "n": 54,
    "median": 0.0354,
    "mean": 0.0468
   }
  },
  "run transcriptions, HF A100 (re-scored)": {
   "n": 54,
   "cer_letters": {
    "n": 54,
    "median": 0.0106,
    "mean": 0.0229
   },
   "cer": {
    "n": 54,
    "median": 0.035,
    "mean": 0.0474
   }
  }
 },
 "timing": {
  "pages": 54,
  "batch": 4,
  "load_seconds": 4.5,
  "gen_seconds": 796.0,
  "pages_per_hour": 244.2,
  "output_tokens": 54542,
  "gpu": "NVIDIA GeForce RTX 3060",
  "transformers": "5.18.0",
  "torch": "2.14.0+cu130"
 },
 "date": "2026-10-09 08:01 IST"
}