Instructions to use Dharma-AI/Dharma-OCR-LITE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dharma-AI/Dharma-OCR-LITE with Transformers:

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

pipe = pipeline("image-text-to-text", model="Dharma-AI/Dharma-OCR-LITE")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Dharma-AI/Dharma-OCR-LITE")
model = AutoModelForMultimodalLM.from_pretrained("Dharma-AI/Dharma-OCR-LITE", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dharma-AI/Dharma-OCR-LITE with vLLM:

Install from pip and serve model

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

SGLang

How to use Dharma-AI/Dharma-OCR-LITE 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 "Dharma-AI/Dharma-OCR-LITE" \
    --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": "Dharma-AI/Dharma-OCR-LITE",
		"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 "Dharma-AI/Dharma-OCR-LITE" \
        --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": "Dharma-AI/Dharma-OCR-LITE",
		"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 Dharma-AI/Dharma-OCR-LITE with Docker Model Runner:
```
docker model run hf.co/Dharma-AI/Dharma-OCR-LITE
```

GabrielPimenta99 commited on Mar 29

Commit

92c4134

verified ·

1 Parent(s): 74f1dd0

Update README.md

Browse files

Files changed (1) hide show

README.md +54 -52

README.md CHANGED Viewed

@@ -34,7 +34,7 @@ DharmaOCR Lite achieves **state-of-the-art performance** on [DharmaOCR-Benchmark
 For the full methodology, training details, and ablation studies, see our paper: **[DharmaOCR: Specialized Small Language Models for Structured OCR that Outperform Open-Source and Commercial Baselines](link_to_paper)**.
 <p align="center">
-  <img src="images/cost_x_score.png" width="600"/>
 </p>
 ## Why DharmaOCR Lite?
@@ -69,57 +69,6 @@ DharmaOCR Lite (3B) **outperforms models with more than twice as many parameters
 <td><b>1.464</b></td>
 </tr>
-<tr><td colspan="4"><br><b>Commercial APIs</b></td></tr>
-<tr>
-<td>Claude Opus 4.6</td>
-<td>0.833</td>
-<td>—</td>
-<td>—</td>
-</tr>
-<tr>
-<td>Gemini 3.1 Pro</td>
-<td>0.820</td>
-<td>—</td>
-<td>—</td>
-</tr>
-<tr>
-<td>GPT-5.4</td>
-<td>0.750</td>
-<td>—</td>
-<td>—</td>
-</tr>
-<tr>
-<td>Google Vision</td>
-<td>0.686</td>
-<td>—</td>
-<td>—</td>
-</tr>
-<tr>
-<td>Google Document AI</td>
-<td>0.640</td>
-<td>—</td>
-<td>—</td>
-</tr>
-<tr>
-<td>GPT-4o</td>
-<td>0.635</td>
-<td>—</td>
-<td>—</td>
-</tr>
-<tr>
-<td>Amazon Textract</td>
-<td>0.618</td>
-<td>—</td>
-<td>—</td>
-</tr>
-<tr>
-<td>Mistral OCR 3</td>
-<td>0.574</td>
-<td>—</td>
-<td>—</td>
-</tr>
 <tr><td colspan="4"><br><b>Open-Source Models</b></td></tr>
 <tr>
@@ -182,6 +131,59 @@ DharmaOCR Lite (3B) **outperforms models with more than twice as many parameters
 <td>21.98</td>
 <td>1.213</td>
 </tr>
 </tbody>
 </table>

 For the full methodology, training details, and ablation studies, see our paper: **[DharmaOCR: Specialized Small Language Models for Structured OCR that Outperform Open-Source and Commercial Baselines](link_to_paper)**.
 <p align="center">
+  <img src="images/cost_x_score.png" width="900"/>
 </p>
 ## Why DharmaOCR Lite?
 <td><b>1.464</b></td>
 </tr>
 <tr><td colspan="4"><br><b>Open-Source Models</b></td></tr>
 <tr>
 <td>21.98</td>
 <td>1.213</td>
 </tr>
+<tr><td colspan="4"><br><b>Commercial APIs</b></td></tr>
+<tr>
+<td>Claude Opus 4.6</td>
+<td>0.833</td>
+<td>—</td>
+<td>—</td>
+</tr>
+<tr>
+<td>Gemini 3.1 Pro</td>
+<td>0.820</td>
+<td>—</td>
+<td>—</td>
+</tr>
+<tr>
+<td>GPT-5.4</td>
+<td>0.750</td>
+<td>—</td>
+<td>—</td>
+</tr>
+<tr>
+<td>Google Vision</td>
+<td>0.686</td>
+<td>—</td>
+<td>—</td>
+</tr>
+<tr>
+<td>Google Document AI</td>
+<td>0.640</td>
+<td>—</td>
+<td>—</td>
+</tr>
+<tr>
+<td>GPT-4o</td>
+<td>0.635</td>
+<td>—</td>
+<td>—</td>
+</tr>
+<tr>
+<td>Amazon Textract</td>
+<td>0.618</td>
+<td>—</td>
+<td>—</td>
+</tr>
+<tr>
+<td>Mistral OCR 3</td>
+<td>0.574</td>
+<td>—</td>
+<td>—</td>
+</tr>
 </tbody>
 </table>