Commit Graph

2837 Commits

Author SHA1 Message Date
oobabooga
6c178b1c91 Add --listen parameter 2023-01-09 19:05:36 -03:00
oobabooga
86092d1879 Update README 2023-01-09 18:58:24 -03:00
oobabooga
9aa51ca227 Update README 2023-01-09 18:18:35 -03:00
oobabooga
fbbad7cf8a Mention units 2023-01-09 18:14:09 -03:00
oobabooga
306be22b8e Add system requirements 2023-01-09 18:12:41 -03:00
oobabooga
13836a37c8 Remove unused parameter 2023-01-09 17:23:43 -03:00
oobabooga
f0013ac8e9 Don't need that 2023-01-09 16:30:14 -03:00
oobabooga
00a12889e9 Refactor model loading function 2023-01-09 16:28:04 -03:00
oobabooga
96a75b616b Update README 2023-01-09 16:19:57 -03:00
oobabooga
f737029ee5 Update README 2023-01-09 16:15:54 -03:00
oobabooga
9704cfaa45 Update README 2023-01-09 16:09:27 -03:00
oobabooga
980f8112a7 Small bug fix 2023-01-09 12:56:54 -03:00
oobabooga
a751d7e693 Don't require GPT-J to be installed to load gpt4chan 2023-01-09 11:39:13 -03:00
oobabooga
6cbfe19c23 Submit with Shift+Enter 2023-01-09 11:22:12 -03:00
oobabooga
e2a917b3bf Update README 2023-01-09 11:11:05 -03:00
oobabooga
0e67ccf607 Implement CPU mode 2023-01-09 10:58:46 -03:00
oobabooga
f2a548c098 Stop generating at \n in chat mode
Makes it a lot more efficient.
2023-01-08 23:00:38 -03:00
oobabooga
a9280dde52 Increase chat height, reorganize things 2023-01-08 20:10:31 -03:00
oobabooga
b871f76aac Better default for chat output length
Ideally, generation should stop at '\n', but this feature is brand new
on transformers (https://github.com/huggingface/transformers/pull/20727)
2023-01-08 15:00:02 -03:00
oobabooga
b801e0d50d Minor changes 2023-01-08 14:37:43 -03:00
oobabooga
730c5562cc Disable gradio analytics 2023-01-08 01:42:38 -03:00
oobabooga
493051d5d5 Chat improvements 2023-01-08 01:33:45 -03:00
oobabooga
4058b33fc9 Improve the chat experience 2023-01-08 01:10:02 -03:00
oobabooga
a0b1b1beb2 Mention gpt4chan's config.json 2023-01-07 23:13:43 -03:00
oobabooga
ef4e610d37 Re-enable the progress bar in notebook mode 2023-01-07 23:01:39 -03:00
oobabooga
c3a0d00715 Name the input box 2023-01-07 22:55:54 -03:00
oobabooga
f76bdadbed Add chat mode 2023-01-07 22:52:46 -03:00
oobabooga
c82ccbb24d Update README 2023-01-07 19:23:59 -03:00
oobabooga
596b40f982 Update readme 2023-01-07 19:22:43 -03:00
oobabooga
0a967bf86d Link galactica 2023-01-07 19:19:55 -03:00
oobabooga
300a500c0b Improve spacings 2023-01-07 19:11:21 -03:00
oobabooga
971fb8e011 Mention the features 2023-01-07 18:40:51 -03:00
oobabooga
29ce69eea7 Update the screenshot 2023-01-07 18:29:32 -03:00
oobabooga
45168e9e7a Update the description 2023-01-07 16:54:49 -03:00
oobabooga
dd1bed2d8b Fix the download script 2023-01-07 16:49:21 -03:00
oobabooga
5345685ead Make paths cross-platform (should work on Windows now) 2023-01-07 16:33:43 -03:00
oobabooga
89fb0a13c5 Add a new preset 2023-01-07 15:13:00 -03:00
oobabooga
342e756878 Better recognize the model sizes 2023-01-07 12:21:04 -03:00
oobabooga
62c4d9880b Fix galactica equations (more) 2023-01-07 12:13:09 -03:00
oobabooga
eeb63b1b8a Fix galactica equations 2023-01-07 01:56:21 -03:00
oobabooga
538998b43b Fix a bug with the greentexts 2023-01-07 01:20:10 -03:00
oobabooga
3aaf5fb4aa Make NovelAI-Sphinx Moth the default preset 2023-01-07 00:49:47 -03:00
oobabooga
898e12058e Clean the convert to torch script 2023-01-07 00:04:52 -03:00
oobabooga
c7b29668a2 Add HTML support for gpt4chan 2023-01-06 23:14:08 -03:00
oobabooga
3d6a3aac73 Reorganize the layout 2023-01-06 22:05:37 -03:00
oobabooga
b53b658320 Update the README 2023-01-06 20:29:00 -03:00
oobabooga
4c89d4ab29 Name the inputs 2023-01-06 20:26:47 -03:00
oobabooga
e5f547fc87 Implement notebook mode 2023-01-06 20:22:26 -03:00
oobabooga
6c02fe7a94 Update the README 2023-01-06 20:09:06 -03:00
oobabooga
eb3aa6b3d7 Update the README 2023-01-06 20:08:43 -03:00