Instructions to use krystv/MIDI_Mamba-159M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use krystv/MIDI_Mamba-159M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="krystv/MIDI_Mamba-159M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("krystv/MIDI_Mamba-159M") model = AutoModelForCausalLM.from_pretrained("krystv/MIDI_Mamba-159M") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use krystv/MIDI_Mamba-159M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "krystv/MIDI_Mamba-159M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "krystv/MIDI_Mamba-159M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/krystv/MIDI_Mamba-159M
- SGLang
How to use krystv/MIDI_Mamba-159M 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 "krystv/MIDI_Mamba-159M" \ --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": "krystv/MIDI_Mamba-159M", "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 "krystv/MIDI_Mamba-159M" \ --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": "krystv/MIDI_Mamba-159M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use krystv/MIDI_Mamba-159M with Docker Model Runner:
docker model run hf.co/krystv/MIDI_Mamba-159M
MIDI Mamba - A MIDI based music generator.
Model Name - MIDI_Mamba-159M_1536VS Model Architecture - Mamba
A MIDI Based music generation model based on Mamba archetecture.
Download Pre-Trained Model from - Huggingface ๐ค.
Some sample generation/output from this model -
These are some sample output generation (not cherry picked). My overall expectation was not matched with this performance so I will continue to work more on that niche. Want to DM me?
My E-Mail - iamhemantindia@protonmail.com Open for any suggestion,advice or collaboration ๐ค.
- Downloads last month
- 6