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

Libraries

How to use rednote-hilab/dots.ocr with Transformers:

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

pipe = pipeline("image-text-to-text", model="rednote-hilab/dots.ocr", 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("rednote-hilab/dots.ocr", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rednote-hilab/dots.ocr with vLLM:

Install from pip and serve model

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

SGLang

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

Update VisionSdpaAttention to support memory efficient backend.

#27

by warrenwjk - opened Sep 13, 2025

base: refs/heads/main

←

from: refs/pr/27

Discussion Files changed

+14

-5

warrenwjk

Sep 13, 2025

Because of a bug (https://github.com/pytorch/pytorch/issues/127523), the memory-efficient backend for scaled_dot_product_attention currently only supports 4D data.

Typically, users only switch to VisionSdpaAttention when their hardware does not support FlashAttention2 (such as Turing architecture GPUs, e.g., the 2080 Ti, and earlier models). However, memory usage increases dramatically with input size. This implementation helps reduce memory consumption, which is the bottleneck in 99% of cases.

Update VisionSdpaAttention to support memory efficient backend.fc8b0b11

redmoe-ai-v1 changed pull request status to merged Sep 13, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment