README.md

metadata

inference: false
language:
  - zh
  - en
license: other
model_creator: baichuan-inc
model_link: https://www.modelscope.cn/models/baichuan-inc/Baichuan2-7B-Chat
model_name: Baichuan2-7B-Chat
model_type: baichuan
pipeline_tag: text-generation
quantized_by: shaowenchen
tasks:
  - text2text-generation
tags:
  - gguf
  - baichuan
  - chinese

Provided files

Name	Quant method	Size
baichuan2-7b-chat.Q2_K.gguf	Q2_K	3.0 GB
baichuan2-7b-chat.Q3_K.gguf	Q3_K	3.5 GB
baichuan2-7b-chat.Q3_K_L.gguf	Q3_K_L	3.8 GB
baichuan2-7b-chat.Q3_K_S.gguf	Q3_K_S	3.2 GB
baichuan2-7b-chat.Q4_0.gguf	Q4_0	4.1 GB
baichuan2-7b-chat.Q4_1.gguf	Q4_1	4.5 GB
baichuan2-7b-chat.Q4_K.gguf	Q4_K	4.3 GB
baichuan2-7b-chat.Q4_K_S.gguf	Q4_K_S	4.1 GB
baichuan2-7b-chat.Q5_0.gguf	Q5_0	4.9 GB
baichuan2-7b-chat.Q5_1.gguf	Q5_1	5.3 GB
baichuan2-7b-chat.Q5_K.gguf	Q5_K	5.0 GB
baichuan2-7b-chat.Q5_K_S.gguf	Q5_K_S	4.9 GB
baichuan2-7b-chat.Q6_K.gguf	Q6_K	5.7 GB
baichuan2-7b-chat.Q8_0.gguf	Q8_0	7.4 GB
baichuan2-7b-chat.gguf	full	14 GB

Usage:

docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/gguf-model-name.gguf hubimage/llama-cpp-python:latest

Provided images

Name	Quant method	Size
shaowenchen/baichuan2-7b-chat-gguf:Q2_K	Q2_K	7.59 GB
shaowenchen/baichuan2-7b-chat-gguf:Q3_K	Q3_K	8.61 GB
shaowenchen/baichuan2-7b-chat-gguf:Q3_K_L	Q3_K_L	9.23 GB
shaowenchen/baichuan2-7b-chat-gguf:Q3_K_S	Q3_K_S	7.93 GB
shaowenchen/baichuan2-7b-chat-gguf:Q4_0	Q4_0	9.6 GB

Usage:

docker run --rm -p 8000:8000 shaowenchen/baichuan2-7b-chat-gguf:Q2_K

and you can view http://localhost:8000/docs to see the swagger UI.