weiweiw
/
Langchain-Chatchat
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
736 Commits 1 Branch 0 Tags 72 MiB
Commit Graph

736 Commits

Author SHA1 Message Date
imClumsyPanda 00cb7bf598 add support for chatglm2-6b-32k 2023-08-01 10:58:05 +08:00
imClumsyPanda dfe7bee243 Merge branch 'master' into dev 2023-07-31 19:54:43 +08:00
Zhi-guo Huang fef931d2b8
Merge pull request #859 from cylee0909/chatglm2cpp 
support chatglm2cpp
 2023-07-28 22:24:51 +08:00
cylee 4235270a32
Merge branch 'dev' into chatglm2cpp 2023-07-28 14:41:14 +08:00
hzg0601 161c9e6c50 fix typo 2023-07-28 03:59:29 +08:00
hzg0601 9326c63a62 Merge branch 'dev' of https://github.com/imClumsyPanda/langchain-ChatGLM into dev 2023-07-27 23:27:53 +08:00
hzg0601 cd91290bfb 删除reqirements的中文 2023-07-27 14:28:58 +08:00
hzg0601 c431bee941 删除requirements的中文 2023-07-27 14:27:11 +08:00
hzg0601 310a865ccd 删除requirements的中文 2023-07-27 14:26:50 +08:00
imClumsyPanda f7a32f9248
Update README.md 2023-07-27 09:23:31 +08:00
imClumsyPanda 36a1c72573
Add files via upload 2023-07-27 09:23:07 +08:00
liunux4odoo 8732dcc1c4 恢复被PR659覆盖的model_config 2023-07-27 08:42:17 +08:00
imClumsyPanda 01a54d1042 add chatglm-fitness-RLHF made by @BoFan-tunning to llm_model_dict in model_config.py 2023-07-26 21:41:27 +08:00
imClumsyPanda 0a062ba07b update img 2023-07-26 21:37:22 +08:00
hzg0601 34a2af118b update model_config.py 2023-07-26 18:04:35 +08:00
hzg0601 e8ff31be1f 1.使api.py里可以使用args.py的参数;2.兼容args.py和model_config.py的控制方式;3.更新fastchat调用模型名的说明 2023-07-26 17:46:02 +08:00
hzg0601 58a5de92a5 1.更改加载lora的方式;2.允许api.py调用args.py的命令行;3. FastChat路径提示 2023-07-26 17:05:37 +08:00
liunux4odoo 5f74f70515 fix: streamlit ui在上传多个文件到知识库时出错 2023-07-25 22:36:49 +08:00
YuhaoWU 466f0c9c97
安装教程conda create新增默认的/envs下面，而不只是只能要额外指定路径 用-p (#482) 
* Update 安装教程中conda虚拟环境的创建与激活
 2023-07-25 16:58:25 +08:00
liunux4odoo 18d453cc18 merge PR 659: make chat api support streaming 2023-07-25 13:23:16 +08:00
imClumsyPanda db80358df8
Update model_config.py 
fix openai api url
 2023-07-25 11:16:02 +08:00
liunux4odoo f21fea41b4 bug fix: 
api.py中,所有chat接口的参数history,其元素应支持None，方便其他框架调用。
否则以history=[[None,'some thing']]调用时会返回422错误。
 2023-07-25 08:53:28 +08:00
Zhi-guo Huang 1f8924eeac
Merge branch 'dev' into chatglm2cpp 2023-07-24 14:44:00 +08:00
lichongyang 62ba7679fe support chatglm2cpp 2023-07-24 14:41:51 +08:00
imClumsyPanda 3f627af745
Update README.md 2023-07-24 08:32:21 +08:00
imClumsyPanda b586ee6e1f
Add files via upload 2023-07-24 08:31:54 +08:00
imClumsyPanda fdd353e48a Merge branch 'master' into dev 2023-07-23 18:40:04 +08:00
imClumsyPanda ff5d2ecc1e update img 2023-07-23 18:39:49 +08:00
imClumsyPanda 0f43845a98 merge master 2023-07-23 18:38:51 +08:00
hzg0601 1e1075b98a Merge branch 'dev' of github.com:imClumsyPanda/langchain-ChatGLM into dev 2023-07-21 23:13:11 +08:00
hzg0601 b2278f2f25 更改api.py的chat函数的history的类型为Optional,修复chat接口不可调用的问题 2023-07-21 23:12:28 +08:00
liunux4odoo a6f42e7c8e fix iss#889: 
when init_model on startup, set llm model's history_len to LLM_HISTORY_LEN from model_config.
 2023-07-21 23:07:50 +08:00
Ma Zhiming 3f76cb5f47
[Fix] INSTALL.md (#907) 
* Update INSTALL.md

* Update INSTALL.md
 2023-07-21 16:42:53 +08:00
hzg0601 3b6819f091 更改默认的LLM_MODEL 2023-07-21 15:35:17 +08:00
hzg0601 6ec1e56e03 Merge branch 'dev' of github.com:imClumsyPanda/langchain-ChatGLM into dev 2023-07-21 15:29:53 +08:00
Zhi-guo Huang acee2d5ad2
Merge pull request #905 from chinainfant/dev 
解决加载ptuning检查点失败的问题
 2023-07-21 15:32:37 +08:00
chinainfant c1c2ed1943
Update loader.py 解决加载ptuning报错的问题 2023-07-21 15:30:19 +08:00
hzg0601 32122ee225 update gitignore 2023-07-21 15:29:36 +08:00
chinainfant ec2bf9757c
Update args.py 将use-ptuning-v2的命名行改为action='store_true' 2023-07-21 15:28:11 +08:00
Zhi-guo Huang 7d37dc876e
Merge pull request #904 from bones-zhu/dev 
1 修复model_config.py的type;2 修改默认的LLM_model;3. 移除chatglm_llm.py的无用模块
 2023-07-21 15:14:33 +08:00
bones-zhu 5479a74789
Update chatglm_llm.py remove unused library 2023-07-21 15:11:51 +08:00
bones-zhu e2eaefc999
Update model_config.py 修改默认的LLM_MODEL 2023-07-21 15:10:13 +08:00
bones-zhu a1b454fc43
Update model_config.py fix type 2023-07-21 15:09:33 +08:00
hzg0601 5f4f8dcedc 解决loader.py中以名称匹配模型式未排除chatglm2的问题 2023-07-21 09:49:18 +08:00
hzg0601 a5294748a4 Merge branch 'dev' of github.com:imClumsyPanda/langchain-ChatGLM into dev 2023-07-21 09:32:19 +08:00
hzg0601 915f4f359a 补充openai的连接失败问题解决方案 2023-07-21 09:29:43 +08:00
imClumsyPanda bf940e9041
Update README.md 2023-07-20 15:06:02 +08:00
imClumsyPanda 2db6604c55
Add files via upload 2023-07-20 15:04:12 +08:00
liunux@home dd3617fcdf 将paddle相关loader改为动态引入，可以在不上传pdf/image知识文件的前提下使用protobuf=4.x。 
这样可以使用最新版streamlit和chainlit。
 2023-07-20 12:32:37 +08:00
Zhi-guo Huang ee7285cd93
在args.py中增加ptuning相关的参数 (#838) 
* 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

* 测试openai接口成功

* add ptuning-v2 dir

* 支持命令行输入ptuning路径

* 在FAQ中给出加载量化版本失败的原因和解决方案

* print error

* udpate

* Update args.py

* debug for fastchat_openai_llm

* temporarily save

* update faq for

---------

Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
Co-authored-by: zg h <bj wang@hzg0601-acer.hundsun.com>
 2023-07-19 23:15:14 +08:00