license: apache-2.0
language:
- zh
- en
library_name: transformers
pipeline_tag: text-generation
原始模型：https://huggingface.co/NousResearch/Nous-Hermes-13b
lora：https://huggingface.co/ziqingyang/chinese-llama-plus-lora-13b
https://huggingface.co/ziqingyang/chinese-alpaca-plus-lora-13b
将Nous-Hermes-13b与chinese-llama-plus-lora-13b和chinese-alpaca-plus-lora-13b进行合并，增强模型的中文能力，不过存在翻译腔
使用项目： https://github.com/ymcui/Chinese-LLaMA-Alpaca
https://github.com/qwopqwop200/GPTQ-for-LLaMa
兼容AutoGPTQ和GPTQ-for-LLaMa
若选择GPTQ-for-LLaMa加载，请设置 Wbits=4 groupsize=128 model_type=llama
Compatible with AutoGPTQ and GPTQ-for-LLaMa
If selecting GPTQ-for-LLaMa loading, please set Wbits=4 groupsize=128 model_type=llama
Text-generation-webui懒人包： https://www.bilibili.com/read/cv23495183
Original model: https://huggingface.co/NousResearch/Nous-Hermes-13b
lora：https://huggingface.co/ziqingyang/chinese-llama-plus-lora-13b
https://huggingface.co/ziqingyang/chinese-alpaca-plus-lora-13b
The Nous-Hermes-13b model is combined with the chinese-llama-plus-lora-13b and chinese-alpaca-plus-lora-13b to enhance the model's Chinese language capabilities, although there may be some translated tone.
Usage projects: https://github.com/ymcui/Chinese-LLaMA-Alpaca
https://github.com/qwopqwop200/GPTQ-for-LLaMa
Compatible with AutoGPTQ and GPTQ-for-LLaMa
If you choose to load GPTQ-for-LLaMa, please set Wbits=4 groupsize=128 model_type=llama