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

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

[m-a-p/YuE-s1-7B-anneal-en-cot](https://huggingface.co/m-a-p/YuE-s1-7B-anneal-en-cot) 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).

Links:
- [4.25bpw-h6](https://huggingface.co/Doctor-Shotgun/YuE-s1-7B-anneal-en-cot-exl2/tree/4.25bpw-h6)
- [5.0bpw-h6](https://huggingface.co/Doctor-Shotgun/YuE-s1-7B-anneal-en-cot-exl2/tree/5.0bpw-h6)
- [6.0bpw-h6](https://huggingface.co/Doctor-Shotgun/YuE-s1-7B-anneal-en-cot-exl2/tree/6.0bpw-h6)
- [8.0bpw-h8](https://huggingface.co/Doctor-Shotgun/YuE-s1-7B-anneal-en-cot-exl2/tree/8.0bpw-h8)