Instructions to use BreadAi/MuseBread with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BreadAi/MuseBread with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BreadAi/MuseBread")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BreadAi/MuseBread") model = AutoModelForCausalLM.from_pretrained("BreadAi/MuseBread") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BreadAi/MuseBread with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BreadAi/MuseBread" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BreadAi/MuseBread", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BreadAi/MuseBread
- SGLang
How to use BreadAi/MuseBread 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 "BreadAi/MuseBread" \ --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": "BreadAi/MuseBread", "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 "BreadAi/MuseBread" \ --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": "BreadAi/MuseBread", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BreadAi/MuseBread with Docker Model Runner:
docker model run hf.co/BreadAi/MuseBread
- Xet hash:
- 2830c5ad9da68174152e81caca5aa65bdcc62a57a6d3f642ddee31c07432fa57
- Size of remote file:
- 84.3 MB
- SHA256:
- 3cfea22969281b475caab07711f13d84b173cb5c76e045a35d19607e4d0ac3fe
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.