Instructions to use breadlicker45/MusePy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use breadlicker45/MusePy with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="breadlicker45/MusePy")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("breadlicker45/MusePy") model = AutoModelForMultimodalLM.from_pretrained("breadlicker45/MusePy") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use breadlicker45/MusePy with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "breadlicker45/MusePy" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "breadlicker45/MusePy", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/breadlicker45/MusePy
- SGLang
How to use breadlicker45/MusePy 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 "breadlicker45/MusePy" \ --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": "breadlicker45/MusePy", "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 "breadlicker45/MusePy" \ --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": "breadlicker45/MusePy", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use breadlicker45/MusePy with Docker Model Runner:
docker model run hf.co/breadlicker45/MusePy
Commit History
Upload 4 files f34c08a
Upload tokenizer.json dc09d65
Delete merges.txt 7390041
Update config.json a64b75b
Upload config.json be790d3
Update config.json b24d460
Update tokenizer_config.json 8e6da9b
Upload 3 files cffc94b
Upload merges.txt 920f1d9
Update README.md dfdd910
Delete tokenize.json 957bbf0
Delete pytorch_model (7).bin 4a8e0e5
Upload 5 files 47ddd19
Rename config (7).json to config.json 489789c
Delete config.json f561d7a
Delete pytorch_model.bin 6888a44
Upload 2 files c7a5e33
Upload 3 files 2335013
Update README.md 06d021e
Update README.md b2ad937
Rename tokenizer_config.json to tokenize.json 7a52d2a
Delete tokenizer.json f2c4d34
Upload 3 files 856b458
Upload tokenizer_config.json a93bb99
Upload tokenizer.json 05c864b
Upload tokenizer.json e648cc5
Upload 2 files ad086f6
Update README.md 157d57a
Update README.md 1829e27
Upload 3 files 8f96aac
Update README.md a9efb8e
Update README.md 722570b
Update README.md 04107ea
initial commit b3c128a
matthew null commited on