Instructions to use typhoon-ai/typhoon-ocr-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use typhoon-ai/typhoon-ocr-7b with Transformers:

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

pipe = pipeline("image-text-to-text", model="typhoon-ai/typhoon-ocr-7b")
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("typhoon-ai/typhoon-ocr-7b")
model = AutoModelForImageTextToText.from_pretrained("typhoon-ai/typhoon-ocr-7b")
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 typhoon-ai/typhoon-ocr-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "typhoon-ai/typhoon-ocr-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typhoon-ai/typhoon-ocr-7b",
		"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/typhoon-ai/typhoon-ocr-7b

SGLang

How to use typhoon-ai/typhoon-ocr-7b 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 "typhoon-ai/typhoon-ocr-7b" \
    --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": "typhoon-ai/typhoon-ocr-7b",
		"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 "typhoon-ai/typhoon-ocr-7b" \
        --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": "typhoon-ai/typhoon-ocr-7b",
		"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 typhoon-ai/typhoon-ocr-7b with Docker Model Runner:
```
docker model run hf.co/typhoon-ai/typhoon-ocr-7b
```

kunato commited on Jun 24, 2025

Commit

9df43b5

verified ·

1 Parent(s): 3d45510

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -105,7 +105,7 @@ from openai import OpenAI
 from PIL import Image
 from typhoon_ocr.ocr_utils import render_pdf_to_base64png, get_anchor_text
-PROMPTS_SYS = {
     "default": lambda base_text: (f"Below is an image of a document page along with its dimensions. "
         f"Simply return the markdown representation of this document, presenting tables in markdown format as they naturally appear.\n"
         f"If the document contains images, use a placeholder like dummy.png for each image.\n"
@@ -128,7 +128,7 @@ def get_prompt(prompt_name: str) -> Callable[[str], str]:
     :param prompt_name: The identifier for the desired prompt.
     :return: The system prompt as a string.
     """
-    return PROMPTS_SYS.get(prompt_name, lambda x: "Invalid PROMPT_NAME provided.")
@@ -209,7 +209,7 @@ print(text_output[0])
 This model only works with the specific prompts defined below, where `{base_text}` refers to information extracted from the PDF metadata using the `get_anchor_text` function from the `typhoon-ocr` package. It will not function correctly with any other prompts.
 ```python
-PROMPTS_SYS = {
     "default": lambda base_text: (f"Below is an image of a document page along with its dimensions. "
         f"Simply return the markdown representation of this document, presenting tables in markdown format as they naturally appear.\n"
         f"If the document contains images, use a placeholder like dummy.png for each image.\n"

 from PIL import Image
 from typhoon_ocr.ocr_utils import render_pdf_to_base64png, get_anchor_text
+PROMPTS = {
     "default": lambda base_text: (f"Below is an image of a document page along with its dimensions. "
         f"Simply return the markdown representation of this document, presenting tables in markdown format as they naturally appear.\n"
         f"If the document contains images, use a placeholder like dummy.png for each image.\n"
     :param prompt_name: The identifier for the desired prompt.
     :return: The system prompt as a string.
     """
+    return PROMPTS.get(prompt_name, lambda x: "Invalid PROMPT_NAME provided.")
 This model only works with the specific prompts defined below, where `{base_text}` refers to information extracted from the PDF metadata using the `get_anchor_text` function from the `typhoon-ocr` package. It will not function correctly with any other prompts.
 ```python
+PROMPTS = {
     "default": lambda base_text: (f"Below is an image of a document page along with its dimensions. "
         f"Simply return the markdown representation of this document, presenting tables in markdown format as they naturally appear.\n"
         f"If the document contains images, use a placeholder like dummy.png for each image.\n"