saber
6a5267aef7
bugfix: linux多卡部署时weight,input不在同一device上,导致RuntimeError
2023-03-27 20:51:05 +08:00
saber
8101d75ab8
fix typo
2023-03-26 15:29:15 +08:00
saber
d9c45f0286
Update README
2023-03-26 15:26:38 +08:00
saber
8826b947c3
多GPU支持, 模型文件夹没有index.json会自动保存模型到multi_gpu_model_cache_dir以支持多GPU
2023-03-26 15:13:44 +08:00
saber
4ee042a8e6
将配置device_map的逻辑抽离, 根据gpu数量自动配置device_map,并且自动适配所有模型
2023-03-26 13:44:10 +08:00
Cherrysaber
dc1a3df1ec
Merge pull request #1 from ChuangLee/main
...
多卡版本
2023-03-26 13:26:33 +08:00
littlepanda0716
023c46a317
update api.py
2023-03-25 18:59:11 +08:00
duzx16
963d5645ef
Merge branch 'main' of github.com:THUDM/ChatGLM-6B
2023-03-25 10:02:58 +08:00
duzx16
ff260ffa51
Update README.md
2023-03-25 10:02:34 +08:00
Zhengxiao Du
bc02336f3e
Merge pull request #221 from ZhangErling/dev_api
...
修复api服务启动错误
2023-03-24 22:13:06 +08:00
Zhengxiao Du
697ee00263
Merge pull request #223 from mojianhao/patch-1
...
Update api.py
2023-03-24 22:12:40 +08:00
holk-h
bf39dac067
Support stream out interruption by using Ctrl+C
2023-03-24 18:34:09 +08:00
Jianhao Mo
1047e446e5
Update api.py
...
bug fix
2023-03-24 16:45:24 +08:00
ZhangErling
acbc2e178a
修复api服务启动错误
...
第31行【API】->【api】会因为大小写原因找不到API
第34行的下划线【chatglm_6b】->【chatglm-6b】会导致模型加载错误
2023-03-24 15:33:42 +08:00
duzx16
28665ade15
Add support for M1 Mac
2023-03-23 22:53:05 +08:00
duzx16
6b13f660bc
Add chatglm-6b-int4-qe
2023-03-23 22:06:15 +08:00
duzx16
955d475079
Add API deployment
2023-03-23 21:59:54 +08:00
duzx16
b0c2b47f5e
Add history in API
2023-03-23 21:42:43 +08:00
Zhengxiao Du
4eca73636e
Merge pull request #159 from LemonQu-GIT/main
...
Add API.py
2023-03-23 21:29:21 +08:00
duzx16
af7f1d4670
Update online demo
2023-03-23 21:23:29 +08:00
Zhengxiao Du
7240b762c3
Merge pull request #207 from yvrjsharma/patch-1
...
Added a link to streaming demo on Huggingface
2023-03-23 21:18:33 +08:00
Yuvraj Sharma
44356fcf3b
Added a link to streaming demo on Huggingface
2023-03-23 18:09:51 +05:30
duzx16
5513dd7d2c
Delete session_state show
2023-03-23 14:46:05 +08:00
lichuang
de9f26c201
初次提交,支持多卡部署。
2023-03-23 10:11:52 +08:00
Zhengxiao Du
5709f7bb9b
Merge pull request #192 from AdamBear/master
...
support stream chat
2023-03-22 15:29:20 +08:00
AdamBear
ee76342382
merge
2023-03-22 15:16:08 +08:00
AdamBear
5040849822
Merge branch 'master' of https://github.com/AdamBear/ChatGLM-6B
2023-03-22 15:13:22 +08:00
AdamBear
ef6b3ff35e
support stream chat
2023-03-22 15:11:21 +08:00
Shaw
292b5684c1
Update link to GLM-130B
2023-03-21 23:32:49 +08:00
duzx16
41b0250ba1
Merge branch 'main' of github.com:THUDM/ChatGLM-6B
2023-03-21 15:29:04 +08:00
duzx16
cbf3d2b666
Fix transformers version
2023-03-21 15:27:17 +08:00
Aohan Zeng
58bfd476e6
Update README.md
2023-03-20 15:39:42 +08:00
Aohan Zeng
c2ff5be358
Update web_demo.py
2023-03-20 15:34:36 +08:00
xiao9905
c3804770e0
Update typewriter-effect examples
2023-03-20 14:25:59 +08:00
duzx16
69bcdcbc4f
Update README
2023-03-19 23:18:53 +08:00
LemonQu
c133b53d51
Add API.py
2023-03-19 22:03:02 +08:00
duzx16
52aa3261d7
Update README
2023-03-19 15:54:04 +08:00
duzx16
17ecc57266
Add newline in cli output
2023-03-19 14:56:34 +08:00
duzx16
8f29459f9a
Update README
2023-03-19 14:37:30 +08:00
duzx16
2ed89f3898
Add support for streaming output
2023-03-19 14:33:05 +08:00
duzx16
6cda36633e
Add gradio in requirements.txt
2023-03-19 10:12:42 +08:00
duzx16
546652e03e
Update README.md
2023-03-18 09:14:17 +08:00
duzx16
5299675425
Update README.md
2023-03-17 23:09:56 +08:00
duzx16
bee0e13817
Merge branch 'dev'
2023-03-17 23:03:03 +08:00
duzx16
f63af3515f
Delete unused code
...
Fix model name
2023-03-17 23:02:44 +08:00
Zhengxiao Du
45f45668d9
Merge pull request #117 from AdamBear/master
...
streamlit based web_demo
2023-03-17 20:58:51 +08:00
duzx16
67ff2198a8
Merge branch 'dev'
2023-03-17 20:31:34 +08:00
Zhengxiao Du
ecd2857c1a
Merge pull request #62 from GanymedeNil/main
...
Add some parameter support in web demo
2023-03-17 17:37:07 +08:00
AdamBear
905aa26b91
Create web_demo2.py
...
Add a steamlit based demo web_demo2.py for better UI.
need to install streamlit and streamlit-chat component fisrt:
pip install streamlit
pip install streamlit-chat
then run with the following:
streamlit run web_demo2.py --server.port 6006
2023-03-17 10:32:06 +08:00
duzx16
d1121e1dae
Update English README
2023-03-16 23:15:02 +08:00