bugfix: models non operational on CPU
30f7268
Tuchuanhuhuhu
commited on
Spaces:
Sleeping
Sleeping
Commit History
Internationalization (#631)
ce202f9
unverified
fix XM Bot
731a989
Tuchuanhuhuhu
commited on
Added support for multi-modal Model: XMBot
03f9025
Tuchuanhuhuhu
commited on
llama支持instruction
ae6a83b
Tuchuanhuhuhu
commited on
将本地LLM设置为全局变量，防止多次调用；Make Class Great Again.
9911cfb
将本地LLM定义为全局变量，防止多次调用。make class great again
90ce14b
多用户使用同一个后端model
066a302
guest
commited on
Fix chatGLM_int4 Error (#586)
a435e54
unverified
Wang Jingye
Chuan Hu
commited on
加入了单轮对话功能
e898b8a
Tuchuanhuhuhu
commited on
解决llama不会自动终止的问题
531abe2
Tuchuanhuhuhu
commited on
减少切换模型时的内存/显存占用
18731f2
Tuchuanhuhuhu
commited on
自动从HG下载llama模型
b48d5f8
Tuchuanhuhuhu
commited on
优化llama模型
53518f7
Tuchuanhuhuhu
commited on
llama支持流式传输
67d913f
Tuchuanhuhuhu
commited on
更新错误处理
0d61cce
Tuchuanhuhuhu
commited on
修复merge导致的bug
8baca88
Tuchuanhuhuhu
commited on
LLaMA + LoRA可以用了
ddd1766
Tuchuanhuhuhu
commited on
拆分requirements
d9e7dbc
Tuchuanhuhuhu
commited on
加入了llama模型支持
7620bdc
Tuchuanhuhuhu
commited on
用语改动
461db8d
Tuchuanhuhuhu
commited on
支持本地embedding
2d5d187
Tuchuanhuhuhu
commited on
加入了运行时切换模型的功能
0127941
Tuchuanhuhuhu
commited on
修复了ChatGLM MPS加速的问题
9a2b13d
Tuchuanhuhuhu
commited on
ChatGLM可以用了
6a2dc28
Tuchuanhuhuhu
commited on
支持ChatGLM
d708c00
Tuchuanhuhuhu
commited on
增加context上限滑动条
86018c8
Tuchuanhuhuhu
commited on
让新增的参数们真正有用
f2c2a56
Tuchuanhuhuhu
commited on
增加了一大堆参数控制
c857ac1
Tuchuanhuhuhu
commited on
重新支持切换api host
cc9e07a
Tuchuanhuhuhu
commited on
统一变量名，修改部分用语
4475ab1
Tuchuanhuhuhu
commited on
重新加入切换模型的功能
c9610d9
Tuchuanhuhuhu
commited on
修复system prompt不可用的问题
de12b06
Tuchuanhuhuhu
commited on
去除chat_func文件，改用类控制模型
77f2c42
Tuchuanhuhuhu
commited on