Commit graph

4687 commits

Author SHA1 Message Date
oobabooga cc757f6226 Small style improvements to the chat tab 2025-06-15 08:32:06 -07:00
oobabooga b279460a81 Improve the wpp style 2025-06-15 08:25:07 -07:00
oobabooga e8dc7b0ee9 Bump exllamav3 to 0.0.4 2025-06-15 08:15:29 -07:00
oobabooga 4fc254c1dd Optimize syntax highlighting on long conversations 2025-06-15 08:13:13 -07:00
oobabooga 609c3ac893 Optimize the end of generation with llama.cpp 2025-06-15 08:03:27 -07:00
oobabooga db7d717df7 Remove images and links from websearch results
This reduces noise a lot
2025-06-14 20:00:25 -07:00
oobabooga e263dbf852 Improve user input truncation 2025-06-14 19:43:51 -07:00
oobabooga 09606a38d3 Truncate web search results to at most 8192 tokens 2025-06-14 19:37:32 -07:00
oobabooga ad0be25c46 Update llama.cpp 2025-06-14 15:00:14 -07:00
oobabooga 7c0225931a Merge branch 'main' into dev 2025-06-14 14:59:37 -07:00
oobabooga 1c1cf09a59 Update workflows 2025-06-14 14:52:49 -07:00
oobabooga 58c3b549ba Merge branch 'main' into dev 2025-06-14 10:16:13 -07:00
oobabooga 8e9c0287aa UI: Fix edge case where gpu-layers slider maximum is incorrectly limited 2025-06-14 10:12:11 -07:00
oobabooga 8e0ef5b419 Hide the header bar on Ctrl+S 2025-06-14 09:09:46 -07:00
oobabooga 1d23159837 Increase the size of the enlarged character profile picture 2025-06-14 08:45:59 -07:00
oobabooga d2da40b0e4 Remember the last selected chat for each mode/character 2025-06-14 08:25:00 -07:00
oobabooga 879fa3d8c4 Improve the wpp style & simplify the code 2025-06-14 07:14:22 -07:00
oobabooga 09eb326486 Merge README.md changes from dev branch 2025-06-13 07:46:43 -07:00
oobabooga dfab11f0b5 Update README 2025-06-13 07:45:42 -07:00
oobabooga 9a2353f97b Better log message when the user input gets truncated 2025-06-13 05:44:02 -07:00
oobabooga 322cd28e24 Update README 2025-06-13 01:27:33 -07:00
oobabooga 7cb650237c Update the README 2025-06-13 01:12:52 -07:00
oobabooga aab28398ef Update README 2025-06-13 01:06:44 -07:00
oobabooga 5ba52967ac Update README 2025-06-13 01:04:41 -07:00
oobabooga b58e80cb99 Update README 2025-06-13 01:02:11 -07:00
Miriam f4f621b215
ensure estimated vram is updated when switching between different models (#7071) 2025-06-13 02:56:33 -03:00
oobabooga f337767f36 Add error handling for non-llama.cpp models in portable mode 2025-06-12 22:17:39 -07:00
oobabooga a25a1fc8d0 Disable message action icons during streaming for better performance 2025-06-12 22:01:02 -07:00
oobabooga 2dee3a66ff Add an option to include/exclude attachments from previous messages in the chat prompt 2025-06-12 21:37:18 -07:00
oobabooga 2cfb77d16f
Merge pull request #7070 from oobabooga/dev
Merge dev branch
2025-06-12 12:38:47 -03:00
oobabooga b4d2a00e20 Update README 2025-06-12 08:35:33 -07:00
oobabooga 9ff5961853
Merge pull request #7067 from oobabooga/dev
Merge dev branch
2025-06-11 11:58:52 -03:00
oobabooga 9d6a7f1bcf Minor changes 2025-06-11 07:55:35 -07:00
oobabooga 004fd8316c Minor changes 2025-06-11 07:49:51 -07:00
oobabooga 570d5b8936 Only save extensions on manual save 2025-06-11 07:39:49 -07:00
oobabooga 27140f3563 Revert "Don't save active extensions through the UI"
This reverts commit df98f4b331.
2025-06-11 07:25:27 -07:00
oobabooga 2ebc8ff252
Merge pull request #7065 from oobabooga/dev
Merge dev branch
2025-06-11 01:09:06 -03:00
oobabooga 13a5288d01 Fix an error when upgrading from cuda 12.4 to cuda 12.8 2025-06-10 21:08:18 -07:00
oobabooga 801db438b0 Undo changes to portable builds 2025-06-10 19:55:40 -07:00
oobabooga 00fbbd6f57 Undo changes to portable builds 2025-06-10 19:54:42 -07:00
oobabooga e8041069e2
Merge pull request #7064 from oobabooga/dev
Merge dev branch
2025-06-10 23:43:10 -03:00
oobabooga fe0685a742 New attempt 2025-06-10 19:42:22 -07:00
oobabooga 036976aeb8
Merge pull request #7063 from oobabooga/dev
Merge dev branch
2025-06-10 23:35:22 -03:00
oobabooga 43fc170224 Fix the Windows workflow 2025-06-10 19:34:41 -07:00
oobabooga e9a433832e
Merge pull request #7062 from oobabooga/dev
Merge dev branch
2025-06-10 23:26:21 -03:00
oobabooga a86a5a026e Fix the GitHub Actions workflows 2025-06-10 19:25:22 -07:00
oobabooga 1e96dcf369
Merge pull request #7057 from oobabooga/dev
Merge dev branch
2025-06-10 23:08:44 -03:00
oobabooga 552cb09f09 Do not bump Transformers to 4.52 on CUDA 12.8
Performance is slow, and the older version works fine with torch 2.7.
2025-06-10 18:45:42 -07:00
LawnMauer bc921c66e5
Load js and css sources in UTF-8 (#7059) 2025-06-10 22:16:50 -03:00
oobabooga 4cf39120fc Fix chat area sometimes not scrolling up to edit message 2025-06-10 18:03:00 -07:00