RichardErkhov/Kas1o_-_SuZhiDiXia-7B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SuZhiDiXia-7B - GGUF

• Model creator: https://huggingface.co/Kas1o/
• Original model: https://huggingface.co/Kas1o/SuZhiDiXia-7B/

Name	Quant method	Size
SuZhiDiXia-7B.Q2_K.gguf	Q2_K	2.89GB
SuZhiDiXia-7B.IQ3_XS.gguf	IQ3_XS	3.18GB
SuZhiDiXia-7B.IQ3_S.gguf	IQ3_S	3.32GB
SuZhiDiXia-7B.Q3_K_S.gguf	Q3_K_S	3.32GB
SuZhiDiXia-7B.IQ3_M.gguf	IQ3_M	3.48GB
SuZhiDiXia-7B.Q3_K.gguf	Q3_K	3.65GB
SuZhiDiXia-7B.Q3_K_M.gguf	Q3_K_M	3.65GB
SuZhiDiXia-7B.Q3_K_L.gguf	Q3_K_L	3.93GB
SuZhiDiXia-7B.IQ4_XS.gguf	IQ4_XS	4.02GB
SuZhiDiXia-7B.Q4_0.gguf	Q4_0	4.2GB
SuZhiDiXia-7B.IQ4_NL.gguf	IQ4_NL	4.22GB
SuZhiDiXia-7B.Q4_K_S.gguf	Q4_K_S	4.23GB
SuZhiDiXia-7B.Q4_K.gguf	Q4_K	4.44GB
SuZhiDiXia-7B.Q4_K_M.gguf	Q4_K_M	4.44GB
SuZhiDiXia-7B.Q4_1.gguf	Q4_1	4.62GB
SuZhiDiXia-7B.Q5_0.gguf	Q5_0	5.03GB
SuZhiDiXia-7B.Q5_K_S.gguf	Q5_K_S	5.03GB
SuZhiDiXia-7B.Q5_K.gguf	Q5_K	5.15GB
SuZhiDiXia-7B.Q5_K_M.gguf	Q5_K_M	5.15GB
SuZhiDiXia-7B.Q5_1.gguf	Q5_1	5.44GB
SuZhiDiXia-7B.Q6_K.gguf	Q6_K	5.91GB
SuZhiDiXia-7B.Q8_0.gguf	Q8_0	7.65GB

Original model description:

datasets: - Seikaijyu/Beautiful-Chinese language: - zh pipeline_tag: text-generation

素质超级低下的模型！

使用优美中国话数据集微调！

格式

使用Qwen/ChatML格式与其交流！

底模

Qwen1.5-7B-Chat

为啥模型卡风格如此抽象?

震撼！