chunzhi/chatgpt_academic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
1,407 Commits 15 Branches 0 Tags
Commit Graph

143 Commits

Author SHA1 Message Date
qingxu fu
6c653734ec Fix 3rd part chatgpt compat 2023-08-26 17:57:59 +08:00
binary-husky
3f4c4ebc29 调整注释 2023-08-25 13:16:18 +08:00
binary-husky
6cc7d4ed69 修复文心一言最大文本长度限制带来的问题 2023-08-25 13:09:08 +08:00
binary-husky
8fce49fa02 支持百度云千帆和文心一言 2023-08-25 12:31:51 +08:00
binary-husky
9720bec5e5 Interface with LLaMa2 from huggingface 2023-08-21 21:54:21 +08:00
qingxu fu
2ff8dc787e interface with ChatGPT-to-API 2023-08-16 22:21:51 +08:00
qingxu fu
cd38d1697c fix missing finish_reason problem 2023-08-16 21:40:34 +08:00
binary-husky
d16329c1af resolve sparkapi on_close error 2023-08-14 11:31:05 +08:00
binary-husky
78a8259b82
Update bridge_all.py 2023-08-14 10:24:59 +08:00
binary-husky
af23730f8f 接入讯飞星火Spark大模型 2023-08-14 03:08:15 +08:00
binary-husky
587c7400d1 xunfei spark api test 2023-08-13 21:34:27 +08:00
binary-husky
3e2e81a968 add chatgpt website 2023-08-13 20:55:18 +08:00
binary-husky
cc1be5585b Merge branch 'master' of https://github.com/hongyi-zhao/gpt_academic into hongyi-zhao-master 2023-08-13 20:50:09 +08:00
binary-husky
7662196514 update tests 2023-08-12 14:09:19 +08:00
binary-husky
184e417fec handle local llm dependency error properly 2023-08-07 02:11:48 +08:00
binary-husky
c17fc2a9b5 我是来自达摩院的大规模语言模型，我叫通义千问。 2023-08-07 01:58:35 +08:00
binary-husky
4d70b3786f interface with qwen 2023-08-07 01:24:41 +08:00
binary-husky
0a37106692 reverse cmd_to_install 2023-08-07 01:11:44 +08:00
binary-husky
57d4541d4e fix minor bug in chatglm-onnx 2023-08-07 01:07:55 +08:00
binary-husky
d7dd586f09 introduce unified base class for local llm models 2023-08-07 00:57:52 +08:00
Hongyi Zhao
bfb7aab4a0 Fix the reverse proxy based OpenAI access via https://github.com/acheong08/ChatGPT-to-API/. 
See https://github.com/binary-husky/gpt_academic/issues/900#issuecomment-1658463065 for more detailed discussions.
 2023-08-02 18:03:49 +08:00
ValeriaWong
c0c337988f feat(chatglm_int8_onnx):纯CPU推理，最多仅需8GB内存，推理速度未测评，token数有限，暂时还不能流式输出 #1008 2023-08-01 00:48:57 +08:00
awwaawwa
e4ba0e6c85
add clear history tips 2023-07-27 23:07:59 +08:00
505030475
4216c5196e verify ignore history practice 2023-07-27 22:30:55 +08:00
binary-husky
e93b6fa3a6 Add GLM INT8 2023-07-24 18:19:57 +08:00
fenglui
5813d65e52 增加chatGLM int4配置支持 小显存也可以选择chatGLM 2023-07-22 08:29:15 +08:00
fenglui
00a3b91f95 fix msg.data.split(DELIMITER) exception when msg.data is int 2023-07-21 03:51:33 +08:00
binary-husky
df90db210c Merge branch 'master' into interface-interlm 2023-07-20 11:40:45 +08:00
binary-husky
73b22f85be compat third party gpt error handle 2023-07-20 11:09:22 +08:00
QQisQQ
0c8c539e9b
解决new bing 报错200 (fix new bing error code 200 ) 
modify from 16e00af9d5

works for my issue:
```
Traceback (most recent call last):
  File "./request_llm/bridge_newbingfree.py", line 152, in run
    asyncio.run(self.async_run())
  File "/root/miniconda3/envs/py311/lib/python3.11/asyncio/runners.py", line 190, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/root/miniconda3/envs/py311/lib/python3.11/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/miniconda3/envs/py311/lib/python3.11/asyncio/base_events.py", line 653, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "./request_llm/bridge_newbingfree.py", line 98, in async_run
    async for final, response in self.newbing_model.ask_stream(
  File "./request_llm/edge_gpt_free.py", line 676, in ask_stream
    async for response in self.chat_hub.ask_stream(
  File "./request_llm/edge_gpt_free.py", line 456, in ask_stream
    self.wss = await self.session.ws_connect(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/miniconda3/envs/py311/lib/python3.11/site-packages/aiohttp/client.py", line 795, in _ws_connect
    raise WSServerHandshakeError(
aiohttp.client_exceptions.WSServerHandshakeError: 200, message='Invalid response status', url=URL('wss://sydney.bing.com/sydney/ChatHub')
```
 2023-07-19 04:39:15 +08:00
binary-husky
fd549fb986 merge success 2023-07-18 19:51:13 +08:00
binary-husky
babb775cfb interface with interlm 2023-07-18 16:33:34 +08:00
binary-husky
6f21ae8939 support claude api 2023-07-16 15:03:05 +08:00
qingxu fu
9b8f160788 up 2023-07-11 15:52:38 +08:00
binary-husky
c010d50716 允许加入ChatGLM微调模型 2023-07-10 03:17:09 +08:00
binary-husky
1fe66f0291 优化azure的体验 2023-07-09 00:20:58 +08:00
qingxu fu
0da6fe78ac 统一azure-gpt-3.5的格式 2023-07-07 10:45:11 +08:00
qingxu fu
be990380a0 Merge branch 'master' of https://github.com/binary-husky/chatgpt_academic into master 2023-07-07 10:42:41 +08:00
qingxu fu
9c0bc48420 修复Azure OpenAI接口的各种bug 2023-07-07 10:42:38 +08:00
binary-husky
2c1d6ac212 修复Organization的bug 2023-07-05 21:14:13 +08:00
binary-husky
e5099e1daa 极少数情况下，openai的官方KEY需要伴随组织编码 2023-07-05 20:05:20 +08:00
binary-husky
cda281f08b 把newbing的cookie加回来 2023-07-05 13:48:50 +08:00
binary-husky
9f8e7a6efa 显示更详细的报错 2023-07-05 13:35:11 +08:00
qingxu fu
57643dd2b6 update error msg 2023-07-05 13:01:06 +08:00
qingxu fu
6bc8a78cfe No more cookie for NewBing! 2023-07-05 12:45:10 +08:00
binary-husky
d2700e97fb 更新openai失效提醒 2023-07-05 11:03:11 +08:00
binary-husky
403667aec1 upgrade chatglm to chatglm2 2023-06-30 12:06:28 +08:00
qingxu fu
057e3dda3c Merge branch 'master' of https://github.com/dackdawn/gpt_academic into dackdawn-master 2023-06-27 15:02:22 +08:00
binary-husky
cd1e4e1ba7
Merge pull request #797 from XiaojianTang/master 
增加azure openai api的支持
 2023-06-21 11:23:41 +10:00
dackdawn
f3e4e26e2f 添加0613模型的声明 
openai对gpt-3.5-turbo的RPM限制是3，而gpt-3.5-turbo-0613的RPM是60，虽然两个模型的内容是一致的，但是选定特定模型可以获得更高的RPM和TPM
 2023-06-19 21:40:26 +08:00