license: apache-2.0
language:
- zh
- en
tags:
- moe
Chinese-Mixtral-Instruct-GGUF
Chinese Mixtral GitHub repository: https://github.com/ymcui/Chinese-Mixtral
This repository contains the GGUF-v3 models (llama.cpp compatible) for Chinese-Mixtral-Instruct (chat/instruction model).
Note: When using instruction/chat model, you MUST follow the official prompt template! Example: chat.sh
Performance
Metric: PPL, lower is better
| Quant | PPL |
|---|---|
| IQ1_S | 27.7911 +/- 0.27400 |
| IQ2_XXS | 6.7233 +/- 0.06118 |
| IQ2_XS | 7.4175 +/- 0.08420 |
| Q2_K | 4.5758 +/- 0.03959 |
| IQ3_XXS | 4.0389 +/- 0.03489 |
| Q3_K | 4.5563 +/- 0.04126 |
| Q4_0 | 3.9757 +/- 0.03455 |
| Q4_K | 3.9265 +/- 0.03407 |
| Q5_0 | 3.9167 +/- 0.03399 |
| Q5_K | 3.9232 +/- 0.03403 |
| Q6_K | 3.9242 +/- 0.03415 |
| Q8_0 | 3.9159 +/- 0.03402 |
| F16 | x |
Due to the file size limitation, for F16 model, please use cat command to concatenate all parts into a single file. You must concatenate these parts in order.
Others
For Hugging Face version, please see: https://huggingface.co/hfl/chinese-mixtral-instruct
Please refer to https://github.com/ymcui/Chinese-Mixtral/ for more details.
Citation
Please consider cite our paper if you use the resource of this repository. Paper link: https://arxiv.org/abs/2403.01851
@article{chinese-mixtral,
title={Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral},
author={Cui, Yiming and Yao, Xin},
journal={arXiv preprint arXiv:2403.01851},
url={https://arxiv.org/abs/2403.01851},
year={2024}
}