---
quantized_by: Ftfyhh
license: apache-2.0
language:
- en
tags:
- music
- llama
base_model: m-a-p/YuE-s1-7B-anneal-en-icl
pipeline_tag: text-generation
---

# YuE-s1-7B-anneal-en-icl-exl2

[m-a-p/YuE-s1-7B-anneal-en-icl](https://huggingface.co/m-a-p/YuE-s1-7B-anneal-en-icl) quantized with Exllamav2. It appears to remain coherent using the default calibration data without adding audio tokens.

Intended to be used with the [WIP exl2 inference repository for YuE](https://github.com/sgsdxzy/YuE-exllamav2).