Instructions to use zenlm/zen-musician with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zenlm/zen-musician with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="zenlm/zen-musician")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zenlm/zen-musician") model = AutoModelForCausalLM.from_pretrained("zenlm/zen-musician", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Zen Musician
Lyrics-to-song / music generation model (stage-1 of the YuE pipeline).
Derived from m-a-p/YuE-s1-7B-anneal-en-cot (Apache-2.0); repackaged by Zen.
Overview
This repository repackages M-A-P's YuE stage-1 7B model (LlamaForCausalLM, hidden 4096 / 32 layers, vocab 83968 - the YuE signature). No weights were trained from scratch by Zen. Full song generation also requires the YuE stage-2 model (m-a-p/YuE-s2-1B-general).
Developed/repackaged by Hanzo AI and the Zoo Labs Foundation.
Model Details
| Attribute | Value |
|---|---|
| Base model | m-a-p/YuE-s1-7B-anneal-en-cot |
| Architecture | LlamaForCausalLM, 7B (stage-1) |
| Vocab | 83968 (YuE) |
| License | Apache 2.0 |
License & Attribution
Apache 2.0. This is a derivative repackaging of YuE-s1-7B-anneal-en-cot by the M-A-P team, released under the Apache License 2.0. All rights and attribution for the underlying model belong to the original authors. See the YuE project for details.
NOTICE
This product includes the YuE (stage-1, 7B) model developed by the M-A-P team, licensed under the Apache License 2.0.
- Downloads last month
- 80