qingxu fu
5c7499cada
compat with some third party api
2023-12-25 17:21:35 +08:00
binary-husky
2c7bba5c63
change dash scope api key check behavior
2023-12-23 21:35:42 +08:00
binary-husky
e22f0226d5
Merge branch 'master' into leike0813-frontier
2023-12-23 21:00:38 +08:00
binary-husky
0f250305b4
add urllib3 version limit
2023-12-23 20:59:32 +08:00
binary-husky
7606f5c130
name fix
2023-12-23 20:55:58 +08:00
binary-husky
4f0dcc431c
Merge branch 'frontier' of https://github.com/leike0813/gpt_academic into leike0813-frontier
2023-12-23 20:42:43 +08:00
binary-husky
e3e9921f6b
correct the misuse of spark image understanding
2023-12-23 17:46:25 +08:00
leike0813
ac3d4cf073
Add support to aliyun qwen online models.
...
Rename model tag "qwen" to "qwen-local"
Add model tag "qwen-turbo", "qwen-plus", "qwen-max"
Add corresponding model interfaces in request_llms/bridge_all.py
Add configuration variable “DASHSCOPE_API_KEY"
Rename request_llms/bridge_qwen.py to bridge_qwen_local.py to distinguish it from the online model interface
2023-12-20 07:37:26 +08:00
binary-husky
d169fb4b16
fix typo
2023-12-15 13:32:39 +08:00
binary-husky
36e19d5202
compat further with one api
2023-12-15 13:16:06 +08:00
binary-husky
8c7569b689
修复protobuf版本错误
2023-12-14 11:00:55 +08:00
binary-husky
d0c2923ab1
Merge pull request #1352 from jlw463195395/master
...
修复deepseekcoder爆显存，加入int8,int4通用加载量化。
2023-12-06 21:37:05 +08:00
Alpha
b0c627909a
更改了一些注释
2023-12-04 12:51:41 +08:00
binary-husky
3c03f240ba
move token limit conf to bridge_all.py
2023-12-04 10:39:10 +08:00
binary-husky
9bfc3400f9
Merge branch 'master' of https://github.com/jlw463195395/gpt_academic into jlw463195395-master
2023-12-04 10:34:19 +08:00
binary-husky
0cd3274d04
combine qwen model family
2023-12-04 10:30:02 +08:00
binary-husky
2cef81abbe
Merge branch 'update-for-qwen' of https://github.com/alphaply/gpt_academic into alphaply-update-for-qwen
2023-12-04 10:09:21 +08:00
Alpha
94ab41d3c0
添加了qwen1.8b模型
2023-12-02 23:12:25 +08:00
Alpha
da376068e1
修复了qwen使用本地模型时候的报错
2023-12-02 21:31:59 +08:00
jlw463195935
4985986243
加入了int4 int8量化，加入默认fp16加载（in4和int8需要安装额外的库）
...
解决连续对话token无限增长爆显存的问题
2023-12-01 16:11:44 +08:00
binary-husky
5b06a6cae5
Merge branch 'master' into frontier
2023-11-24 03:28:07 +08:00
qingxu fu
5d5695cd9a
version 3.61
2023-11-24 03:19:20 +08:00
qingxu fu
fd72894c90
修复错误的class命名
2023-11-24 02:42:58 +08:00
qingxu fu
c1abec2e4b
Merge branch 'master' of https://github.com/binary-husky/chatgpt_academic into master
2023-11-24 02:36:39 +08:00
qingxu fu
9916f59753
接入deepseek-coder
2023-11-24 02:35:44 +08:00
binary-husky
e6716ccf63
添加zhipuai依赖安装提醒
2023-11-24 01:47:03 +08:00
Marroh
b470af7c7b
遵循PEP 328优化太长的import
2023-11-22 13:20:56 +08:00
spike
aa341fd268
适配星火大模型图片理解 增加上传图片view
2023-11-15 10:09:42 +08:00
binary-husky
682898a3ba
支持gpt-4-v处理多张图片
2023-11-13 13:21:33 +08:00
binary-husky
9a21e13d33
支持gpt-4-vision-preview
2023-11-13 13:10:59 +08:00
binary-husky
b9b7bf38ab
修复插件导入时的pytorch加载问题
2023-11-13 00:15:15 +08:00
binary-husky
69f37df356
紧急修复终结点覆盖错误的问题
2023-11-12 22:15:54 +08:00
qingxu fu
1335da4f45
Merge branch 'frontier' into master_autogen
2023-11-11 23:24:21 +08:00
qingxu fu
2d91e438d6
修正internlm输入设备bug
2023-11-11 23:22:50 +08:00
qingxu fu
f7f6db831b
处理模型兼容的一些细节
2023-11-11 22:35:06 +08:00
qingxu fu
a655ce1f00
Merge branch 'frontier' into master_autogen
2023-11-11 22:03:20 +08:00
qingxu fu
28119e343c
将autogen大模型调用底层hook掉
2023-11-11 22:01:19 +08:00
qingxu fu
f75e39dc27
修复本地模型在Windows下的加载BUG
2023-11-11 21:11:55 +08:00
qingxu fu
2570e4b997
remove revision
2023-11-11 18:17:58 +08:00
qingxu fu
2b917edf26
修复本地模型在windows上的兼容性
2023-11-11 17:58:17 +08:00
qingxu fu
107ea868e1
API2D自动对齐
2023-11-10 23:08:56 +08:00
binary-husky
caf45ef740
Merge pull request #1244 from awwaawwa/fix_gpt_35_16k_maxtoken
...
修改 gpt-3.5-turbo-16k 系列模型 max_token 为 16385
2023-11-10 12:55:02 +08:00
qingxu fu
a1a91c25a5
移除重复项
2023-11-10 12:53:03 +08:00
qingxu fu
2912eaf082
Merge branch 'master' of https://github.com/Skyzayre/gpt_academic into Skyzayre-master2
2023-11-10 12:51:50 +08:00
qingxu fu
0ff750b60a
修改缩进
2023-11-10 12:40:25 +08:00
qingxu fu
8ad2a2bb86
Merge branch 'master' of https://github.com/samxiaowastaken/gpt_academic into samxiaowastaken-master
2023-11-10 12:37:30 +08:00
awwaawwa
8d94564e67
修改 gpt-3.5-turbo-16k 系列模型 max_token 为 16385
...
根据 https://platform.openai.com/docs/models/gpt-3-5 ，这个16k的3.5上下文窗口其实是16385
2023-11-07 15:59:07 +08:00
binary-husky
996057e588
support chatglm3
2023-11-07 15:41:04 +08:00
binary-husky
8e375b0ed2
support chatglm3
2023-11-07 14:07:30 +08:00
binary-husky
5192d316f0
Merge branch 'frontier'
2023-11-07 11:40:27 +08:00
