Yifan
|
cf0240cfa8
|
Merge pull request #3 from yfyang86/mac-m1-dev
[Document] 更新Mac部署
|
2 years ago |
Yifan
|
2ac5b2223d
|
[Document] 更新Mac部署
[Document] 更新Mac部署
- FILE: README.md/README_end.md
- ADD: OPENMP; MPS
# 具体内容
以[chatglm-6b-int4](https://huggingface.co/THUDM/chatglm-6b-int4)量化模型为例,做如下配置:
- 安装libomp的步骤;
- 对量化后模型等配置gcc编译项;
- 量化后模型启用MPS的解释;
- 缩短文本长度。
|
2 years ago |
Yifan
|
8983d4b7bc
|
Merge pull request #2 from yfyang86/mac-m1-dev
[Document] 更新Mac部署
|
2 years ago |
Yifan
|
16b3a43717
|
Merge pull request #1 from yfyang86/mac-m1-dev
[Document] 更新Mac部署
|
2 years ago |
Yifan
|
2629a55222
|
[Document] 更新Mac部署
[Document] 更新Mac部署
- FILE: README.md; README_en.md
- ADD: OPENMP; MPS
# 具体内容
以[chatglm-6b-int4](https://huggingface.co/THUDM/chatglm-6b-int4)量化模型为例,做如下配置:
- 安装libomp的步骤;
- 对量化后模型等配置gcc编译项;
- 量化后模型启用MPS的解释。
|
2 years ago |
Yifan
|
b13f1a63f3
|
[Document] 更新Mac部署
[Document] 更新Mac部署
- FILE: README.md; README_en.md
- ADD: OPENMP; MPS
# 具体内容
以[chatglm-6b-int4](https://huggingface.co/THUDM/chatglm-6b-int4)量化模型为例,做如下配置:
- 安装libomp的步骤;
- 对量化后模型等配置gcc编译项;
- 量化后模型启用MPS的解释。
|
2 years ago |
Yifan
|
f1fa8db8f2
|
[Document] 更新Mac部署
[Document] 更新Mac部署
- FILE: Readme.md
- ADD: OPENMP; MPS
|
2 years ago |
Zhengxiao Du
|
baec759103
|
Merge pull request #861 from hiyouga/patch-2
Update PROJECT.md
|
2 years ago |
hoshi-hiyouga
|
78615dc155
|
Update PROJECT.md
|
2 years ago |
duzx16
|
c95b6b9d0d
|
Update english README
|
2 years ago |
duzx16
|
5dee917a67
|
Update PROJECT.md
|
2 years ago |
duzx16
|
5fde7328ec
|
Add version
|
2 years ago |
duzx16
|
7862b18b8a
|
Update web demo
|
2 years ago |
hwaking
|
0903d2377f
|
Update web_demo2.py
当前MAX_BOXES与MAX_TURNS不生效导致单次对话不终止显存不断增加最后显存溢出问题,修改最大对话轮数和最大历史对话数量使其生效,逻辑为历史最大对话框记录轮数达到MAX_BOXES时截断历史对话为最近MAX_TURNS数。
|
2 years ago |
duzx16
|
2a9119bc96
|
Update train_chat.sh
|
2 years ago |
duzx16
|
d2fcbc74c6
|
Merge branch 'main' of github.com:THUDM/ChatGLM-6B
|
2 years ago |
duzx16
|
3956b8b326
|
Update conversation data instruction
|
2 years ago |
liushu
|
286b4cb8f4
|
add project
|
2 years ago |
Zhengxiao Du
|
cb3cdbcaf8
|
Merge pull request #811 from jsl9208/main
添加ModelWhale相关项目链接
|
2 years ago |
Zhengxiao Du
|
fe8ff9d661
|
Merge pull request #739 from hiyouga/patch-1
添加较成熟的开源微调项目ChatGLM-Efficient-Tuning
|
2 years ago |
Zhengxiao Du
|
b817da1d02
|
Merge pull request #780 from imClumsyPanda/main
更新对基于 langchain 的 ChatGLM 应用项目 langchain-chatglm 的介绍
|
2 years ago |
Zhengxiao Du
|
90a86d707e
|
Merge pull request #802 from ninehills/patch-1
增加友情链接 ChatGLM-OpenAI-API
|
2 years ago |
Shilong Jiang
|
73a4f77bd0
|
Add online projects to readme
|
2 years ago |
Tao Yang
|
53c8d21f0d
|
增加友情链接 ChatGLM-OpenAI-API
|
2 years ago |
duzx16
|
aeced3619b
|
Update README
|
2 years ago |
duzx16
|
7aad40565d
|
Update README
|
2 years ago |
duzx16
|
2e9f5371ee
|
Add improvement project
|
2 years ago |
imClumsyPanda
|
8d89e283d7
|
update README.md and PROJECT.md
|
2 years ago |
duzx16
|
0a05145a2c
|
Update PROJECT.md
|
2 years ago |
hoshi-hiyouga
|
afe08a19cc
|
添加较成熟的开源微调项目ChatGLM-Efficient-Tuning
|
2 years ago |
duzx16
|
9f571c42f2
|
Update PROJECT.md
|
2 years ago |
Zhengxiao Du
|
edb127326a
|
Merge pull request #719 from LuckyZY/main
添加友情链接
|
2 years ago |
LuckyZY
|
a6af7c4bcb
|
添加友情链接
|
2 years ago |
duzx16
|
8e83083d7f
|
Update README.md
|
2 years ago |
Zhengxiao Du
|
44c9b8b8d1
|
Merge pull request #707 from makenv/ptuning-web-demo
ptuning-v2微调适配的web_demo.
|
2 years ago |
Zhengxiao Du
|
1ce0b767b7
|
Merge pull request #685 from yanqiangmiffy/patch-2
Update PROJECT.md
|
2 years ago |
Zhengxiao Du
|
67c1d447e1
|
Merge pull request #704 from binary-husky/patch-1
Add project reference to https://github.com/binary-husky/chatgpt_academic
|
2 years ago |
is
|
8e85119d7c
|
ptuning适配的web_demo.
|
2 years ago |
binary-husky
|
8a953dfaf0
|
Update PROJECT.md
|
2 years ago |
yanqiangmiffy
|
7df785fc4e
|
Update PROJECT.md
|
2 years ago |
duzx16
|
01e6313abf
|
Fix multi-gpu loading
|
2 years ago |
duzx16
|
9e61c3ea9b
|
Add INT8 model and cloud
|
2 years ago |
duzx16
|
b3f232d980
|
Update slack link
|
2 years ago |
duzx16
|
4f95c09a3b
|
Add multi-gpu deployment
|
2 years ago |
duzx16
|
90f2e47f54
|
Merge branch 'dev' into dev_multi_gpu
# Conflicts:
# README.md
# api.py
# cli_demo.py
# requirements.txt
|
2 years ago |
duzx16
|
ffcb1f9394
|
Remove save_pretrained
|
2 years ago |
duzx16
|
e182e13cf5
|
Update instructions
|
2 years ago |
duzx16
|
c34ad40092
|
Add instructions
|
2 years ago |
duzx16
|
8633db1503
|
Merge branch 'main' of github.com:THUDM/ChatGLM-6B
|
2 years ago |
duzx16
|
5ade1e4055
|
Update loading instructions
|
2 years ago |