Instructions to use samaritan-ai/dots-ocr-samaritan-hebrew with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use samaritan-ai/dots-ocr-samaritan-hebrew with Transformers:

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

pipe = pipeline("image-text-to-text", model="samaritan-ai/dots-ocr-samaritan-hebrew", trust_remote_code=True)
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 AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("samaritan-ai/dots-ocr-samaritan-hebrew", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use samaritan-ai/dots-ocr-samaritan-hebrew with vLLM:

Install from pip and serve model

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

SGLang

How to use samaritan-ai/dots-ocr-samaritan-hebrew 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 "samaritan-ai/dots-ocr-samaritan-hebrew" \
    --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": "samaritan-ai/dots-ocr-samaritan-hebrew",
		"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 "samaritan-ai/dots-ocr-samaritan-hebrew" \
        --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": "samaritan-ai/dots-ocr-samaritan-hebrew",
		"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 samaritan-ai/dots-ocr-samaritan-hebrew with Docker Model Runner:
```
docker model run hf.co/samaritan-ai/dots-ocr-samaritan-hebrew
```

dots.ocr · Samaritan → Hebrew (checkpoint-350)

Fine-tuned dots.ocr for Samaritan manuscript OCR, emitting modern Hebrew transcriptions (RTL).

This repository contains a merged full checkpoint (base + LoRA) selected by a full validation sweep (ocr_cer on 494 OCR/grounding samples). Adapter step: 350.

Highlights

Item	Value
Base	`rednote-hilab/dots.ocr` (~3.04B)
Method	LoRA r=32, α=64, RSLoRA; vision + language targets; vision merger trained densely
Train recipe	`max_pixels=3_500_000`, `max_seq_length=6144`, bf16, grad accum 16
Selected checkpoint	`checkpoint-350` (merged)
Val OCR CER (micro)	0.0463
Val OCR exact match	0.470
Val OCR CER median / p90	0.0025 / 0.161
Layout F1 (14 layout pages)	0.857
JSON valid rate (layout)	1.0

Plain cer in multi-task dumps is dominated by the small layout subset. Prefer ocr_cer for this model.

Intended use

Page / line OCR of Samaritan manuscript images into Hebrew text
Optional layout JSON / grounding prompts inherited from dots.ocr

Not a general multilingual OCR replacement for the base model. Outside Samaritan→Hebrew, prefer the upstream checkpoint.

Quick start

import torch
from transformers import AutoModelForCausalLM, AutoProcessor
from qwen_vl_utils import process_vision_info
from PIL import Image

model_id = "samaritan-ai/dots-ocr-samaritan-hebrew"  # update if you rename the repo
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    attn_implementation="sdpa",  # or flash_attention_2
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Match the fine-tune pixel budget (also set in preprocessor_config.json here)
ip = processor.image_processor
ip.min_pixels, ip.max_pixels = 3136, 3_500_000
ip.size = {**getattr(ip, "size", {}), "shortest_edge": 3136, "longest_edge": 3_500_000}

image = Image.open("page.jpg").convert("RGB")
prompt = "Extract the text content from this image."
messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": prompt},
    ],
}]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
    text=[text], images=image_inputs, videos=video_inputs,
    padding=True, return_tensors="pt",
).to(model.device)

with torch.inference_mode():
    out = model.generate(**inputs, max_new_tokens=2048, do_sample=False)
print(processor.tokenizer.decode(out[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

Prompt modes (same family as dots.ocr)

OCR: Extract the text content from this image.
Layout + text (JSON): dots.ocr layout-all prompt
Grounding OCR: bbox-conditioned extract prompt

Training summary

Toolkit: dotsocr-ft (local fine-tune stack for dots.ocr / PAGEXML)
Data: PAGEXML-prepared Samaritan pages; packed train/val with sparse grounding (--grounding-per-page 2)
Hardware: dual RTX 3090 (24 GB); early stop on generative CER (n=16 probe during train)
Final selection: full data/val.packed.jsonl sweep over checkpoint-{150,200,250,300,350,400} ranked by ocr_cer

Comparative full-val OCR CER (494 samples):

Adapter	ocr_cer	exact	median	p90
checkpoint-300	0.0412	0.445	0.0038	0.760
checkpoint-350	0.0463	0.470	0.0025	0.161
checkpoint-250	0.0500	0.421	0.0098	0.176
checkpoint-200	0.0653	0.362	0.0179	0.176
checkpoint-400	0.0702	0.486	0.0013	0.096
checkpoint-150	0.1675	0.221	0.0402	0.786

checkpoint-350 was chosen as the balanced production checkpoint (strong micro CER and healthy tail vs checkpoint-300’s high p90).

Requirements

transformers==4.51.x (dots.ocr remote code target)
huggingface-hub>=0.30,<1.0
qwen-vl-utils, torch with bf16 GPU recommended
trust_remote_code=True (ships modeling_*.py / configuration_dots.py)

License & attribution

Fine-tune / card: use under the same spirit as the base release; respect the upstream dots.ocr LICENSE AGREEMENT (MIT-based with additional acceptable-use terms) included in this repo.
Base model: rednote-hilab/dots.ocr · GitHub
Do not use for prohibited digitization / privacy-invasive extraction as defined by the upstream agreement.

Citation

If you use this model, please cite the upstream dots.ocr work and note this Samaritan→Hebrew fine-tune (checkpoint-350).

Downloads last month: -

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for samaritan-ai/dots-ocr-samaritan-hebrew

Base model

dots-studio/dots.ocr

Adapter

(1)

this model

samaritan-ai
/

dots-ocr-samaritan-hebrew