Commit Graph

303 Commits (5dee917a67fa5e0fe29762aedfba51aca096f005)
 

Author SHA1 Message Date
duzx16 08d880141d Fix revision for loading model
2 years ago
duzx16 08f0731e94 Merge branch 'main' of github.com:THUDM/ChatGLM-6B
2 years ago
duzx16 c206e7d9ad Update requirements.txt
2 years ago
Shaw fdc2c7f70d
Update README.md
2 years ago
Shaw 7e84262ddc
Update README.md
2 years ago
Aohan Zeng ba93cafa7d
Update README.md
2 years ago
Aohan Zeng 9853cd2c97
Update README.md
2 years ago
Aohan Zeng 4c923c4ed7
Update p-tuning-v2
2 years ago
Aohan Zeng 99875468dd
Update README.md
2 years ago
duzx16 24e24d5d6c Fix model path
2 years ago
duzx16 5e818065e4 Update memory requirement
2 years ago
duzx16 d2645d8816 Update batch size
2 years ago
duzx16 971a6fbb20 Updaet ADGEN link
2 years ago
duzx16 77da046839 Update model path
2 years ago
duzx16 a100769153 Add P-Tuning v2
2 years ago
duzx16 50a7c3c530 Merge branch 'main' of github.com:THUDM/ChatGLM-6B
2 years ago
duzx16 968a30672a Add P-Tuning v2
2 years ago
Shaw ee7fa65ebd
Update README.md
2 years ago
Shaw 32d625463c
Update README.md
2 years ago
duzx16 323ce7c865 Add instructions for installing Git LFS
2 years ago
duzx16 fc55c075fe Update README
2 years ago
duzx16 7d7d87c4bd Update README
2 years ago
duzx16 343e7bc7b6 Fix model path
2 years ago
Zhengxiao Du 25356d6441
Merge pull request #225 from holk-h/main
2 years ago
duzx16 6fc8141a9c Revert "Fix typo"
2 years ago
duzx16 c6790a09f0 Fix typos
2 years ago
Zhengxiao Du 43b7241e67
Merge pull request #241 from Cherrysaber/dev-multi-gpus
2 years ago
duzx16 1c6002f3f1 Fix typo
2 years ago
Zhengxiao Du 3e9e02fb1d
Merge pull request #235 from imClumsyPanda/main
2 years ago
duzx16 bc973445c8 Merge branch 'main' into dev_api
2 years ago
duzx16 9addb875ca Add links
2 years ago
saber c313af0639 Add support for manual device_map; auto-config if None
2 years ago
saber c31d9c0984 Move import statement into function to avoid dependency
2 years ago
saber 6a5267aef7 bugfix: linux多卡部署时weight,input不在同一device上,导致RuntimeError
2 years ago
saber 8101d75ab8 fix typo
2 years ago
saber d9c45f0286 Update README
2 years ago
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
2 years ago
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
2 years ago
Cherrysaber dc1a3df1ec
Merge pull request #1 from ChuangLee/main
2 years ago
littlepanda0716 023c46a317 update api.py
2 years ago
duzx16 963d5645ef Merge branch 'main' of github.com:THUDM/ChatGLM-6B
2 years ago
duzx16 ff260ffa51 Update README.md
2 years ago
Zhengxiao Du bc02336f3e
Merge pull request #221 from ZhangErling/dev_api
2 years ago
Zhengxiao Du 697ee00263
Merge pull request #223 from mojianhao/patch-1
2 years ago
holk-h bf39dac067 Support stream out interruption by using Ctrl+C
2 years ago
Jianhao Mo 1047e446e5
Update api.py
2 years ago
ZhangErling acbc2e178a
修复api服务启动错误
2 years ago
duzx16 28665ade15 Add support for M1 Mac
2 years ago
duzx16 6b13f660bc Add chatglm-6b-int4-qe
2 years ago
duzx16 955d475079 Add API deployment
2 years ago