liang tongtong
|
3682020c20
|
添加webui readme说明
|
2023-04-11 05:38:27 +00:00 |
liang tongtong
|
57c3cac3bb
|
Webui更新说明
1、自动读取knowledge_based_chatglm.py中LLM及embedding模型枚举,选择后点击setting进行模型加载,可随时切换模型进行测试
2、可手动调节保留对话历史长度,可根据显存大小自行调节
3、添加上传文件功能,通过下拉框选择已上传的文件,点击loading加载文件,过程中可随时更换加载的文件
4、底部添加use via API可对接到自己系统
TODO:
1、添加模型加载进度条
2、添加输出内容及错误提示
3、国家化语言切换
4、引用标注
5、添加插件系统(可基础lora训练等)
|
2023-04-11 04:30:36 +00:00 |
imClumsyPanda
|
f7f40406c4
|
update requirements.txt
|
2023-04-11 11:09:38 +08:00 |
imClumsyPanda
|
a0a8257b93
|
Merge pull request #51 from calcitem/readme
Update README
|
2023-04-11 00:21:37 +08:00 |
Calcitem
|
9445822224
|
Update README
About how to solve "Resource not found".
|
2023-04-11 00:15:16 +08:00 |
imClumsyPanda
|
866e9950e8
|
use RetrievalQA instead of ChatVectorDBChain
|
2023-04-10 23:41:27 +08:00 |
imClumsyPanda
|
481aab97cb
|
use RetrievalQA instead of ChatVectorDBChain
|
2023-04-10 22:55:37 +08:00 |
imClumsyPanda
|
12ee17f3b3
|
use RetrievalQA instead of ChatVectorDBChain
|
2023-04-10 22:55:22 +08:00 |
imClumsyPanda
|
2240ed1ec2
|
update requirements.txt
|
2023-04-09 23:31:26 +08:00 |
imClumsyPanda
|
3dc5860cfe
|
Add llm_model_dict to choose llm and add chatglm-6b-int4 as an option
|
2023-04-09 23:23:11 +08:00 |
imClumsyPanda
|
6d5b143811
|
Add llm_model_dict to choose llm and add chatglm-6b-int4 as an option
|
2023-04-09 23:20:05 +08:00 |
imClumsyPanda
|
7720bb58e0
|
Add llm_model_dict to choose llm and add chatglm-6b-int4 as an option
|
2023-04-09 23:10:44 +08:00 |
imClumsyPanda
|
384d705101
|
update README_en.md
|
2023-04-09 23:04:32 +08:00 |
imClumsyPanda
|
efa1338eb5
|
Merge pull request #41 from calcitem/patch-1
Update README.md
|
2023-04-09 10:33:03 +08:00 |
Calcitem
|
f5503ac041
|
Update README.md
|
2023-04-09 10:30:01 +08:00 |
imClumsyPanda
|
79acbfb8c3
|
更新 README_en.md
|
2023-04-08 16:49:38 +08:00 |
imClumsyPanda
|
cd58b414ac
|
更新 README.md
|
2023-04-08 16:48:55 +08:00 |
imClumsyPanda
|
7e3b87dcd6
|
update requirements.txt
|
2023-04-08 09:23:58 +08:00 |
imClumsyPanda
|
49eda9935e
|
update README_en.md
|
2023-04-07 18:33:57 +08:00 |
imClumsyPanda
|
dcaec899e6
|
update README_en.md
|
2023-04-07 18:24:59 +08:00 |
imClumsyPanda
|
9bb7c219ff
|
Merge pull request #28 from lastrei/master
根据4.7日更新代码,解决冲突
|
2023-04-07 12:22:22 +08:00 |
zhangwei
|
1b1107315c
|
根据4.7日更新代码,解决冲突
新增ernie系列模型作为embedding model,默认依旧使用GanymedeNil/text2vec-large-chinese
显存不足时可尝试使用ernie-tiny作为embedding模型
调用方式为embeddings = HuggingFaceEmbeddings(model_name=embedding_model_dict["ernie-tiny"], )
|
2023-04-07 12:01:15 +08:00 |
imClumsyPanda
|
f239881b6f
|
Create LICENSE
|
2023-04-07 11:41:10 +08:00 |
littlepanda0716
|
3cec586487
|
update README.md
|
2023-04-07 11:15:03 +08:00 |
littlepanda0716
|
e04085e380
|
add torch_gc to clear gpu cache in knowledge_based_chatglm.py
|
2023-04-07 11:02:23 +08:00 |
littlepanda0716
|
60d752bc18
|
add torch_gc to clear gpu cache in knowledge_based_chatglm.py
|
2023-04-07 10:53:03 +08:00 |
littlepanda0716
|
c4b52dda72
|
add torch_gc to clear gpu cache in knowledge_based_chatglm.py
|
2023-04-07 10:46:02 +08:00 |
littlepanda0716
|
5664d1ff62
|
add torch_gc to clear gpu cache in knowledge_based_chatglm.py
|
2023-04-07 10:45:44 +08:00 |
littlepanda0716
|
3cbc6aa77c
|
update knowledge_based_chatglm.py
|
2023-04-07 10:11:26 +08:00 |
littlepanda0716
|
dfe966ed41
|
update chatglm_llm.py
|
2023-04-07 09:58:44 +08:00 |
littlepanda0716
|
befcdf6e32
|
update README.md
|
2023-04-07 09:48:59 +08:00 |
littlepanda0716
|
0d0550525a
|
update README.md
|
2023-04-07 09:48:59 +08:00 |
imClumsyPanda
|
63d900607f
|
Merge pull request #17 from myml/memory
fix: 修复chatglm模型被复制,显存占用过多
|
2023-04-07 09:43:49 +08:00 |
littlepanda0716
|
51c44e3e0a
|
update chatglm_llm.py
|
2023-04-07 09:28:45 +08:00 |
imClumsyPanda
|
3ab6dbee00
|
Merge pull request #21 from thomas-yanxin/master
Update requirements.txt
|
2023-04-05 21:58:38 +08:00 |
thomas-yanxin
|
b6e603a33c
|
Update requirements.txt
|
2023-04-05 21:39:42 +08:00 |
myml
|
bed03a6ff1
|
fix: 修复chatglm模型被复制,显存占用过多
model作为类成员会在类实例化时进行一次复制
这导致每询问一个问题显存占用就会翻倍
通过将model改成全局变量修复这个问题
|
2023-04-05 01:17:26 +08:00 |
littlepanda0716
|
1851b4f074
|
update requirements.txt
|
2023-04-03 21:07:41 +08:00 |
littlepanda0716
|
a8abbff4bb
|
update requirements.txt
|
2023-04-03 20:37:54 +08:00 |
littlepanda0716
|
6762ab442f
|
update function name and requirements.txt
|
2023-04-03 19:15:08 +08:00 |
littlepanda0716
|
ca902e1a7b
|
update function name and requirements.txt
|
2023-04-03 19:13:34 +08:00 |
imClumsyPanda
|
f0250eef38
|
Merge pull request #1 from zx2021/master
修复requirements.txt文件
|
2023-03-31 22:04:10 +08:00 |
littlepanda0716
|
0ddffff3fc
|
update requirements.txt
|
2023-03-31 22:02:41 +08:00 |
zx2021
|
7d59541718
|
Update requirements.txt
修复了运行pip install -r requirements.txt提示ERROR: Invalid requirement: '"detectron2@git+https://github.com/facebookresearch/detectron2.git@v0.6#egg=detectron2"' (from line 4 of requirements.txt)
Hint: = is not a valid operator. Did you mean == ?的错误
|
2023-03-31 21:49:16 +08:00 |
zx2021
|
2d3ea9830e
|
Update requirements.txt
修复运行pip install -r requirements.txt提示ERROR: Invalid requirement: '"detectron2@git+https://github.com/facebookresearch/detectron2.git@v0.6#egg=detectron2"' (from line 4 of requirements.txt)
Hint: = is not a valid operator. Did you mean == ?的错误
|
2023-03-31 21:47:58 +08:00 |
littlepanda0716
|
2edb920b24
|
first commit
|
2023-03-31 20:23:49 +08:00 |
littlepanda0716
|
f17d26addf
|
first commit
|
2023-03-31 20:09:40 +08:00 |