Chinese-Mixtral-GGUF

Chinese Mixtral GitHub repository: https://github.com/ymcui/Chinese-Mixtral

This repository contains the GGUF-v3 models (llama.cpp compatible) for Chinese-Mixtral (this is not a chat/instruction model).

Performance

Metric: PPL, lower is better

Quant	PPL
IQ1_S	20.7314 +/- 0.22627
IQ2_XXS	8.5981 +/- 0.09267
IQ2_XS	6.9784 +/- 0.07476
Q2_K	5.1846 +/- 0.05533
IQ3_XXS	4.5990 +/- 0.04969
Q3_K	4.5545 +/- 0.04893
Q4_0	4.4917 +/- 0.04844
Q4_K	4.4488 +/- 0.04813
Q5_0	4.4224 +/- 0.04753
Q5_K	4.4192 +/- 0.04768
Q6_K	4.4092 +/- 0.04758
Q8_0	4.4076 +/- 0.04746
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

• If you have questions/issues regarding this model, please submit an issue through https://github.com/ymcui/Chinese-Mixtral/.

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}
}