glide-the
|
c389f1a33a
|
增加fastchat打字机输出
|
2023-07-16 01:29:51 +08:00 |
liunux4odoo
|
5cbb86a823
|
rewrite streamlit ui with streamlit-chatbox;fix bugs (#850)
|
2023-07-15 22:05:57 +08:00 |
taokuizu
|
df3744f501
|
fix Non-UTF-8 code starting with \xe5 (#849)
|
2023-07-15 21:08:47 +08:00 |
taokuizu
|
3b93902670
|
修改README.md,添加支持的LLM(bloomz-7b1,bloom-3b,baichuan-7b,vicuna-13b-delta-v1.1) (#845)
|
2023-07-15 00:29:16 +08:00 |
imClumsyPanda
|
1cd4ba8a51
|
Update README.md
|
2023-07-14 18:43:24 +08:00 |
imClumsyPanda
|
3107f777fa
|
Add files via upload
|
2023-07-14 18:42:57 +08:00 |
hzg0601
|
db0fcf4e03
|
print error
|
2023-07-14 15:10:33 +08:00 |
hzg0601
|
760abab1d7
|
Merge branch 'dev' of github.com:hzg0601/langchain-ChatGLM-annotation into dev
merge upstream dev
|
2023-07-14 13:45:48 +08:00 |
hzg0601
|
3d082bf566
|
在FAQ中给出加载量化版本失败的原因和解决方案
|
2023-07-14 13:45:07 +08:00 |
hzg0601
|
57cb6b05de
|
add moss-int4
|
2023-07-13 22:21:00 +08:00 |
zg h
|
43d1bf4fb3
|
支持命令行输入ptuning路径
|
2023-07-13 22:10:54 +08:00 |
hzg0601
|
f68d347c25
|
add ptuning-v2 dir
|
2023-07-13 21:22:35 +08:00 |
glide-the
|
c5bc21781c
|
修改模型生成的调用方式,兼容Chain调用
修改模型切换的bug
|
2023-07-12 23:09:28 +08:00 |
Zhi-guo Huang
|
ca13ab8173
|
测试OPENAI接口成功 (#813)
|
2023-07-11 23:40:49 +08:00 |
hzg0601
|
1940da0adf
|
测试openai接口成功
|
2023-07-11 23:35:24 +08:00 |
imClumsyPanda
|
979dfa1976
|
Merge remote-tracking branch 'origin/dev' into dev
|
2023-07-11 21:49:02 +08:00 |
imClumsyPanda
|
2371feaa4f
|
update README.md
|
2023-07-11 21:48:50 +08:00 |
hzg0601
|
a8e820359a
|
Merge branch 'dev' of github.com:hzg0601/langchain-ChatGLM-annotation into dev
merge dev.
|
2023-07-11 21:44:59 +08:00 |
hzg0601
|
48ce8b1c84
|
pull dev
|
2023-07-11 21:43:26 +08:00 |
Zhi-guo Huang
|
64f22a9e53
|
修改默认的多卡部署方案,基本保证针对新模型也不会失败 (#788)
* 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项
* 更新FAQ,增加了[Errno 110] Connection timed out的原因与解决方案
* 修改loader.py中load_in_8bit失败的原因和详细解决方案
* update loader.py
* stream_chat_bing
* 修改stream_chat的接口,在请求体中选择knowledge_base_id;增加stream_chat_bing接口
* 优化cli_demo.py的逻辑:支持 输入提示;多输入;重新输入
* update cli_demo.py
* 按照review建议进行修改
* 修改默认的多卡部署方案,基本保证针对新模型也不会失败
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
|
2023-07-11 20:24:49 +08:00 |
imClumsyPanda
|
e02f49a49e
|
Merge branch 'dev' into dev
|
2023-07-11 20:24:18 +08:00 |
imClumsyPanda
|
3a6a6fa8f6
|
update model_config.py
|
2023-07-11 20:19:50 +08:00 |
imClumsyPanda
|
7480005822
|
Merge branch 'master' into dev
|
2023-07-11 20:18:40 +08:00 |
imClumsyPanda
|
2d1ad18a4f
|
update README.md
|
2023-07-11 20:18:24 +08:00 |
NieLamu
|
ff5f73e041
|
feat: fastapi 接口优化 (#684)
1. 接口增加参数校验,防止攻击
2. 优化接口参数和逻辑
3. 规范接口错误响应
4. 增加接口描述
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
|
2023-07-11 19:52:52 +08:00 |
Zhi-guo Huang
|
a5ca4bf26a
|
1.增加对llama-cpp模型的支持;2.增加对bloom/chatyuan/baichuan模型的支持;3. 修复多GPU部署的bug;4. 修复了moss_llm.py的bug;5. 增加对openai支持(没有api,未测试);6. 支持在多卡情况自定义设备GPU (#664)
* 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项
* 更新FAQ,增加了[Errno 110] Connection timed out的原因与解决方案
* 修改loader.py中load_in_8bit失败的原因和详细解决方案
* update loader.py
* stream_chat_bing
* 修改stream_chat的接口,在请求体中选择knowledge_base_id;增加stream_chat_bing接口
* 优化cli_demo.py的逻辑:支持 输入提示;多输入;重新输入
* update cli_demo.py
* add bloom-3b,bloom-7b1,ggml-vicuna-13b-1.1
* 1.增加对llama-cpp模型的支持;2.增加对bloom模型的支持;3. 修复多GPU部署的bug;4. 增加对openai支持(没有api,未测试);5.增加了llama-cpp模型部署的说明
* llama模型兼容性说明
* modified: ../configs/model_config.py
modified: ../docs/INSTALL.md
在install.md里增加对llama-cpp模型调用的说明
* 修改llama_llm.py以适应llama-cpp模型
* 完成llama-cpp模型的支持;
* make fastchat and openapi compatiable
* 1. 修复/增加对chatyuan,bloom,baichuan-7等模型的支持;2. 修复了moss_llm.py的bug;
* set default model be chatglm-6b
* 在多卡情况下也支持自定义GPU设备
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
|
2023-07-11 19:36:50 +08:00 |
kztao
|
cf0f1d6625
|
Update README.md, 0.1.16版本已经支持删除知识库中的文件 (#792)
* Update README.md
* fix:The knowledge base name cannot be empty.
* Update webui.py
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
|
2023-07-11 19:20:47 +08:00 |
kztao
|
c564c91a82
|
fix:The knowledge base name cannot be empty. (#793)
* fix:The knowledge base name cannot be empty.
* Update webui.py
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
|
2023-07-11 19:18:24 +08:00 |
imClumsyPanda
|
80af725a41
|
Update README.md
|
2023-07-11 19:15:09 +08:00 |
imClumsyPanda
|
f0ea1c1bb0
|
Add files via upload
|
2023-07-11 19:14:41 +08:00 |
ysyx2008
|
5f0697799a
|
解决 image_loader.py 运行时报错“ModuleNotFoundError: No module named 'configs'”的问题。 (#795)
|
2023-07-11 19:12:46 +08:00 |
imClumsyPanda
|
a8a3ea9ca2
|
Update README.md
|
2023-07-07 10:27:00 +08:00 |
imClumsyPanda
|
af4ddc8923
|
Add files via upload
|
2023-07-07 10:26:23 +08:00 |
hzg0601
|
300d287d61
|
修改默认的多卡部署方案,基本保证针对新模型也不会失败
|
2023-07-06 04:47:44 +08:00 |
imClumsyPanda
|
e68bc53cab
|
Update README.md
|
2023-07-05 09:32:40 +08:00 |
imClumsyPanda
|
de98919fe6
|
Add files via upload
|
2023-07-05 09:32:05 +08:00 |
Fan
|
10abb8d781
|
添加启动API的参数,支持https、wss方式API调用 (#728)
* update README.md
* 添加启动API的参数,支持https、wss方式API调用。(CA证书自备)
添加启动API服务的markdown说明文档。
---------
Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
Co-authored-by: 一帆 <zhang.f@digitalcnzz.com>
|
2023-07-04 19:52:17 +08:00 |
stc2001
|
7217e3391d
|
Update model_config.py (#768)
添加ChatGLM2-6b-int4和ChatGLM2-6b-int8
|
2023-07-04 19:04:57 +08:00 |
imClumsyPanda
|
967ac2ed2b
|
merge master
|
2023-07-02 22:18:59 +08:00 |
imClumsyPanda
|
80ecc08044
|
update README.md
|
2023-07-02 22:16:58 +08:00 |
Zhi-guo Huang
|
c52308d605
|
1. 修改stream_chat的接口,在请求体中选择knowledge_base_id;2. 增加stream_chat_bing接口;3. 增加了调用流式接口的方法说明;4. 优化cli_demo.py的逻辑:支持 输入提示;多输入;重新输入 (#630)
* 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项
* 更新FAQ,增加了[Errno 110] Connection timed out的原因与解决方案
* 修改loader.py中load_in_8bit失败的原因和详细解决方案
* update loader.py
* stream_chat_bing
* 修改stream_chat的接口,在请求体中选择knowledge_base_id;增加stream_chat_bing接口
* 优化cli_demo.py的逻辑:支持 输入提示;多输入;重新输入
* update cli_demo.py
* 按照review建议进行修改
|
2023-07-02 21:54:12 +08:00 |
hzg0601
|
43fae98bb5
|
按照review建议进行修改
|
2023-07-02 20:47:27 +08:00 |
zzxs
|
6ab496ea4a
|
Update api.py (#628)
修复websocket的伪流式输出
|
2023-07-02 13:42:53 +08:00 |
imClumsyPanda
|
b922970ac2
|
Update README.md
|
2023-07-01 10:16:47 +08:00 |
imClumsyPanda
|
393bd400cb
|
Add files via upload
|
2023-07-01 10:16:09 +08:00 |
Jingsong-Yan
|
421ce3da3a
|
Add device_map config to support chatglm2-6b (#734)
chatglm-6b和chatglm2-6b的参数命名不一致,本次提交旨在解决chatglm2-6b device_map 创建的问题。在chatglm_auto_configure_device_map 函数中新增了chatglm2-6b device_map 创建的相关代码。
|
2023-06-30 21:08:38 +08:00 |
neverless00
|
51ed739d6c
|
fix 2 bugs on streamlit demo (#719)
|
2023-06-30 21:01:41 +08:00 |
jinke
|
3c66fc3b18
|
向Readme添加Docker整合包描述 (#746)
|
2023-06-30 07:19:07 +08:00 |
imClumsyPanda
|
1612c89160
|
Update README.md
|
2023-06-29 12:53:27 +08:00 |
imClumsyPanda
|
2bda2cf7a6
|
Update README.md
|
2023-06-29 12:52:51 +08:00 |