imClumsyPanda
|
e42e6a01d0
|
Delete llm directory
|
2023-04-18 19:42:54 +08:00 |
imClumsyPanda
|
b03deaa253
|
update qr_code.jpg
|
2023-04-18 19:22:01 +08:00 |
imClumsyPanda
|
1df41bd41f
|
update qr_code.jpg
|
2023-04-18 19:20:58 +08:00 |
imClumsyPanda
|
383f58273e
|
Add files via upload
|
2023-04-18 19:17:13 +08:00 |
imClumsyPanda
|
f606fa1261
|
Delete qr_code.jpg
|
2023-04-18 19:17:02 +08:00 |
imClumsyPanda
|
641299768a
|
Add files via upload
|
2023-04-18 19:16:18 +08:00 |
Shilong Jiang
|
4cbb6b4253
|
doc: Add modelwhale notebook links
|
2023-04-18 19:11:06 +08:00 |
imClumsyPanda
|
86c4147bd0
|
Merge pull request #128 from Viscount/dev
1. 参考ChatGLM-6B代码实现模型多卡部署
|
2023-04-18 18:54:34 +08:00 |
Liao Zhenyu
|
edbe155c2e
|
1. 参考ChatGLM-6B代码实现模型多卡部署
|
2023-04-18 15:54:51 +08:00 |
wangxinkai
|
5a0429b2af
|
feat: add api for knowledge_based QA
|
2023-04-18 10:08:36 +08:00 |
wangxinkai
|
3eaa25c9ba
|
feat: add api for knowledge_based QA
|
2023-04-18 10:08:13 +08:00 |
imClumsyPanda
|
a231f92d98
|
修复 webui.py 中 llm_history_len 和 vector_search_top_k 显示值与启动设置默认值不一致的问题
|
2023-04-18 10:07:35 +08:00 |
imClumsyPanda
|
ca49799fb2
|
add nltk_data
|
2023-04-18 10:07:19 +08:00 |
imClumsyPanda
|
79f1420a14
|
Add files via upload
|
2023-04-18 10:07:19 +08:00 |
imClumsyPanda
|
b1641a3e34
|
Add files via upload
|
2023-04-18 10:07:19 +08:00 |
imClumsyPanda
|
048c71f893
|
fix bug in webui.py
|
2023-04-18 10:07:19 +08:00 |
imClumsyPanda
|
8ae84c6c93
|
update local_doc_qa.py
|
2023-04-17 23:59:22 +08:00 |
imClumsyPanda
|
4df8bb92b1
|
Merge pull request #111 from drunken-boat/master
fix: typo
|
2023-04-17 13:48:34 +08:00 |
Tara
|
b8498f5602
|
fix: typo
fix a typo in README.md line 180.
|
2023-04-17 10:39:15 +08:00 |
imClumsyPanda
|
10b345f738
|
Merge branch 'hot-fix'
|
2023-04-16 23:41:34 +08:00 |
imClumsyPanda
|
4aadcfa042
|
add nltk_data
|
2023-04-16 23:41:10 +08:00 |
imClumsyPanda
|
081fac5343
|
add nltk_data
|
2023-04-16 23:38:25 +08:00 |
imClumsyPanda
|
033e8959ca
|
Add files via upload
|
2023-04-16 23:07:11 +08:00 |
imClumsyPanda
|
91ed178e86
|
Add files via upload
|
2023-04-16 22:19:28 +08:00 |
imClumsyPanda
|
f87a5f59ca
|
fix bug in webui.py
|
2023-04-16 08:59:06 +08:00 |
Calcitem
|
88941d3938
|
Add release.py
|
2023-04-16 02:47:31 +08:00 |
Calcitem
|
b2917b0007
|
Splice README.md
|
2023-04-16 02:21:26 +08:00 |
imClumsyPanda
|
59375244b6
|
修复 webui.py 中 llm_history_len 和 vector_search_top_k 显示值与启动设置默认值不一致的问题
|
2023-04-15 20:01:54 +08:00 |
imClumsyPanda
|
e679136b25
|
Merge pull request #104 from thaumstrial/master
Support for p-tuningv2
|
2023-04-15 14:59:10 +08:00 |
Thaumstrial
|
2cd52f6605
|
Support p-tuning-v2
|
2023-04-15 14:43:12 +08:00 |
glide-the
|
fe29a4556e
|
Merge pull request #102 from glide-the/dev
子文件的__pycache__忽略
|
2023-04-15 12:45:58 +08:00 |
glide-the
|
da6be02589
|
子文件的__pycache__忽略
|
2023-04-15 12:45:00 +08:00 |
imClumsyPanda
|
dc0cdfba90
|
Merge branch 'dev'
|
2023-04-15 10:38:41 +08:00 |
imClumsyPanda
|
0234a95fd7
|
update README.md and README_en.md
|
2023-04-15 10:34:54 +08:00 |
imClumsyPanda
|
abb1bc8956
|
update README.md and README_en.md
|
2023-04-15 10:32:21 +08:00 |
imClumsyPanda
|
f56f325b91
|
update README.md
|
2023-04-15 09:56:50 +08:00 |
imClumsyPanda
|
5e75016787
|
update README.md
|
2023-04-15 01:03:44 +08:00 |
imClumsyPanda
|
0f043c33f2
|
update webui.py
|
2023-04-14 23:42:28 +08:00 |
imClumsyPanda
|
12f5458374
|
update webui.py
|
2023-04-14 23:30:37 +08:00 |
Calcitem
|
6bb9dcccce
|
Update .gitignore
|
2023-04-14 23:05:40 +08:00 |
imClumsyPanda
|
8c469fda31
|
update webui.py
|
2023-04-14 22:57:07 +08:00 |
imClumsyPanda
|
5c3497912c
|
update webui.py
|
2023-04-14 22:55:51 +08:00 |
imClumsyPanda
|
1be430be2a
|
update README.md
|
2023-04-14 22:55:07 +08:00 |
imClumsyPanda
|
512241195d
|
Delete .idea directory
|
2023-04-14 22:45:41 +08:00 |
fengyunzaidushi
|
877f722863
|
Merge pull request #97 from fengyunzaidushi/dev
修改入群码为二群二维码
|
2023-04-14 22:39:16 +08:00 |
fengyu
|
a4f1ff6b45
|
修改入群码为二群二维码
|
2023-04-14 22:35:15 +08:00 |
glide-the
|
2ce70b3d95
|
Merge pull request #95 from glide-the/dev
chatglm_with_shared_memory_openai_llm:agent
|
2023-04-14 22:18:03 +08:00 |
glide-the
|
57efaa5492
|
chatglm_with_shared_memory_openai_llm:这个demo,基于openai的任务处理,实现本地文…
…档调用链的示例,可以使用chatgml处理一部分任务事件,也可以使用chatgml来完成记忆共享(SharedMemory),至于为什么使用openai原因主要有两个现象,第一点,因为大模型chatgml受限,导致很多langchain的demo只能部分实现,跟群主聊了下,这种问题只能通过微调模型,增加一部分指令集和状态术语的数据集进去,微调方案只能大家自己尝试了,对显卡要去较高.当然也可以考虑只训练一个任务格式化的gml,模型微调参考这个仓库的方式 https://github.com/liucongg/ChatGLM-Finetuning
|
2023-04-14 22:15:02 +08:00 |
fengyunzaidushi
|
0aa04e954f
|
Merge pull request #94 from fengyunzaidushi/dev
Q7: 本项目用到的模型权重文件百度网盘地址:
|
2023-04-14 22:13:30 +08:00 |
fengyu
|
c1720d1997
|
Merge remote-tracking branch 'origin/dev' into dev
|
2023-04-14 22:02:51 +08:00 |