xiaoshuai111 / lawyer-llama-13b-v2

The unofficial implementation of Lawyer LLaMA, with a quantization Q4_0

13B

47 Pulls Updated 7 weeks ago

7 weeks ago

4df9caf6b814 · 7.6GB

model
llama
·
13.3B
·
Q4_0
params
{"num_ctx":4096,"stop":["<|im_start|>","<|im_end|>"],"temperature":1}
template
{{ if .System }}<|im_start|>system {{ .System }}<|im_end|>{{ end }}<|im_start|>user {{ .Prompt }}<|im_end|> <|im_start|>assistant
system
你是人工智能法律助手“Lawyer LLaMA”，能够回答与中国法律相关的问题。\n

Readme

When using the GPU, the required Ollama Docker image version is 0.1.32; for the CPU, the version is not restricted, but the speed will be slower.

template = qwen1.5

Citation

@misc{huang2023lawyer,
title={Lawyer LLaMA Technical Report},
author={Quzhe Huang and Mingxu Tao and Chen Zhang and Zhenwei An and Cong Jiang and Zhibin Chen and Zirui Wu and Yansong Feng},
year={2023},
eprint={2305.15062},
archivePrefix={arXiv},
primaryClass={cs.CL}
}

@misc{Lawyer-LLama,
title={Lawyer Llama},
author={Quzhe Huang and Mingxu Tao and Chen Zhang and Zhenwei An and Cong Jiang and Zhibin Chen and Zirui Wu and Yansong Feng},
year={2023},
publisher={GitHub},
journal={GitHub repository},
howpublished={\url{https://github.com/AndrewZhe/lawyer-llama}},
}