Instructions to use stanford-crfm/music-large-800k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stanford-crfm/music-large-800k with Transformers:

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

pipe = pipeline("text-generation", model="stanford-crfm/music-large-800k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("stanford-crfm/music-large-800k")
model = AutoModelForCausalLM.from_pretrained("stanford-crfm/music-large-800k")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use stanford-crfm/music-large-800k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stanford-crfm/music-large-800k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stanford-crfm/music-large-800k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/stanford-crfm/music-large-800k

SGLang

How to use stanford-crfm/music-large-800k 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 "stanford-crfm/music-large-800k" \
    --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": "stanford-crfm/music-large-800k",
		"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 "stanford-crfm/music-large-800k" \
        --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": "stanford-crfm/music-large-800k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use stanford-crfm/music-large-800k with Docker Model Runner:
```
docker model run hf.co/stanford-crfm/music-large-800k
```

This is a Large (780M parameter) Transformer trained for 800k steps on arrival-time encoded music from the Lakh MIDI dataset, MetaMidi dataset, and transcripts of the FMA audio dataset and 450k commercial music records (transcribed using Google Magenta's ISMIR 2022 music transcription model). This model was trained with anticipation.

References for the Anticipatory Music Transformer

The Anticipatory Music Transformer paper is available on ArXiv.

The full model card is available here.

Code for using this model is available on GitHub.

See the accompanying blog post for additional discussion of anticipatory models.

Downloads last month: 739

Safetensors

Model size

0.8B params

Tensor type

F32

Spaces using stanford-crfm/music-large-800k 6

Paper for stanford-crfm/music-large-800k

Anticipatory Music Transformer

Paper • 2306.08620 • Published Jun 14, 2023 • 10