Quantization made by Richard Erkhov.

chinese-mixtral - GGUF

Model creator: https://huggingface.co/hfl/
Original model: https://huggingface.co/hfl/chinese-mixtral/

Name	Quant method	Size
chinese-mixtral.Q2_K.gguf	Q2_K	16.12GB
chinese-mixtral.Q3_K_S.gguf	Q3_K_S	19.03GB
chinese-mixtral.Q3_K.gguf	Q3_K	21.0GB
chinese-mixtral.Q3_K_M.gguf	Q3_K_M	21.0GB
chinese-mixtral.Q3_K_L.gguf	Q3_K_L	22.51GB
chinese-mixtral.IQ4_XS.gguf	IQ4_XS	23.63GB
chinese-mixtral.Q4_0.gguf	Q4_0	24.63GB
chinese-mixtral.IQ4_NL.gguf	IQ4_NL	24.91GB
chinese-mixtral.Q4_K_S.gguf	Q4_K_S	24.91GB
chinese-mixtral.Q4_K.gguf	Q4_K	26.49GB
chinese-mixtral.Q4_K_M.gguf	Q4_K_M	26.49GB
chinese-mixtral.Q4_1.gguf	Q4_1	27.32GB
chinese-mixtral.Q5_0.gguf	Q5_0	30.02GB
chinese-mixtral.Q5_K_S.gguf	Q5_K_S	30.02GB
chinese-mixtral.Q5_K.gguf	Q5_K	30.95GB
chinese-mixtral.Q5_K_M.gguf	Q5_K_M	30.95GB
chinese-mixtral.Q5_1.gguf	Q5_1	32.71GB
chinese-mixtral.Q6_K.gguf	Q6_K	35.74GB
chinese-mixtral.Q8_0.gguf	Q8_0	46.22GB

Original model description:

license: apache-2.0 language: - zh - en tags: - moe

Chinese-Mixtral

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

This repository contains Chinese-Mixtral, which is further pre-trained on Mixtral-8x7B-v0.1.

Note: this is a foundation model, which is not suitable for conversation, QA, etc.

Others

For LoRA-only model, please see: https://huggingface.co/hfl/chinese-mixtral-lora
For GGUF model (llama.cpp compatible), please see: https://huggingface.co/hfl/chinese-mixtral-gguf
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}
}