Instructions to use mooncakex/blip-art with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mooncakex/blip-art with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="mooncakex/blip-art")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mooncakex/blip-art") model = AutoModelForMultimodalLM.from_pretrained("mooncakex/blip-art", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mooncakex/blip-art with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mooncakex/blip-art" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mooncakex/blip-art", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mooncakex/blip-art
- SGLang
How to use mooncakex/blip-art 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 "mooncakex/blip-art" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mooncakex/blip-art", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "mooncakex/blip-art" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mooncakex/blip-art", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mooncakex/blip-art with Docker Model Runner:
docker model run hf.co/mooncakex/blip-art
Download training_args.bin from mooncakex/blip-art: direct link, hf CLI and curl.
- Browser
- Download file 3.64 kB
-
https://huggingface.co/mooncakex/blip-art/resolve/main/training_args.bin
- Command line
-
hf download hf://mooncakex/blip-art/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/mooncakex/blip-art/resolve/main/training_args.bin
3.64 kB
- Xet hash:
- 58a9a08a7514e0d593182e2eda3017ead0c4e8aaa02187a80cdec7717ddc8591
- Size of remote file:
- 3.64 kB
- SHA256:
- 08b146d8cfce7fc990c1a6b8434e0d24f231f4ad803c0df3f92c7acf9b572291
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.