oobabooga/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2026-01-06 00:30:13 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity
4597 commits 6 branches 91 tags 66 MiB
Commit graph

4597 commits

This branch
This branch
All branches
Author SHA1 Message Date
oobabooga 263b5d5557 Use html2text to extract the text of web searches without losing formatting 2025-06-09 17:55:26 -07:00
oobabooga f5a5d0c0cb Add the URL of web attachments to the prompt 2025-06-09 17:32:25 -07:00
oobabooga 747a4a0e56 Reposition the ... typing dots 2025-06-09 13:41:29 -07:00
oobabooga 14efd42084 Improve scroll performance by disabling hover effects during scroll 2025-06-09 11:43:15 -07:00
oobabooga 1602ac1c8f Improve the style of thinking blocks in dark mode 2025-06-09 09:03:39 -07:00
oobabooga eefbf96f6a Don't save truncation_length to user_data/settings.yaml 2025-06-08 22:14:56 -07:00
oobabooga 80637cae28 Add version to portable build folder names 2025-06-08 21:55:49 -07:00
oobabooga f9a007c6a8 Properly filter out failed web search downloads from attachments 2025-06-08 19:25:23 -07:00
oobabooga f3388c2ab4 Fix selecting next chat when deleting with active search 2025-06-08 18:53:04 -07:00
oobabooga 4a369e070a Add buttons for easily deleting past chats 2025-06-08 18:47:48 -07:00
oobabooga 0b8d2d65a2 Minor style improvement 2025-06-08 18:11:27 -07:00
oobabooga 06dfb7e772 Improve the style of the hover menu 2025-06-08 18:03:07 -07:00
oobabooga b5e021fc49 Make the dark theme darker 2025-06-08 17:44:04 -07:00
oobabooga e976a5ddc7 Re-highlight code blocks when switching light/dark themes 2025-06-08 17:35:36 -07:00
oobabooga 7ed1926ce7 Small change after previous commit 2025-06-08 15:38:40 -07:00
oobabooga ff01bcb870 Use user_data/cache/gradio for Gradio temp files 2025-06-08 15:33:05 -07:00
oobabooga f81b1540ca Small style improvements 2025-06-08 15:19:25 -07:00
oobabooga eb0ab9db1d Fix light/dark theme persistence across page reloads 2025-06-08 15:04:05 -07:00
oobabooga 78899244d5 Remove settings-template.yaml 2025-06-08 09:40:09 -07:00
oobabooga 1f1435997a Don't show the new 'Restore character' button in the Chat tab 2025-06-08 09:37:54 -07:00
oobabooga 84f66484c5 Make it optional to paste long pasted content to an attachment 2025-06-08 09:31:38 -07:00
oobabooga 42e7864d62 Reorganize the Session tab 2025-06-08 09:21:23 -07:00
oobabooga af6bb7513a Add back the "Save UI defaults" button 
It's useful for saving extensions settings.
 2025-06-08 09:09:36 -07:00
oobabooga 1cab149c1a Remove the contrastive search preset 2025-06-07 22:26:13 -07:00
oobabooga ae150fa24f Remove the null preset 2025-06-07 22:25:46 -07:00
oobabooga 1bdf11b511 Use the Qwen3 - Thinking preset by default 2025-06-07 22:23:09 -07:00
oobabooga 0dbc4cbc71 Add Qwen3 presets 2025-06-07 22:20:58 -07:00
oobabooga fe955cac1f Small UI changes 2025-06-07 22:15:19 -07:00
oobabooga caf9fca5f3 Avoid some code repetition 2025-06-07 22:11:35 -07:00
oobabooga 3650a6fd1f Small UI changes 2025-06-07 22:02:34 -07:00
oobabooga 6436bf1920
More UI persistence: presets and characters (#7051) 2025-06-08 01:58:02 -03:00
oobabooga 35ed55d18f
UI persistence (#7050) 2025-06-07 22:46:52 -03:00
rakha abadi susilo db847eed4c
Add RTX 50XX Nvidia blackwell support (ExLlamaV2/V3 and Transformers) (#7011) 
---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2025-06-07 21:44:15 -03:00
oobabooga 2d263f227d Fix the chat input reappearing when the page is reloaded 2025-06-06 22:38:20 -07:00
oobabooga 379dd01ca7 Filter out failed web search downloads from attachments 2025-06-06 22:32:07 -07:00
oobabooga f8f23b5489 Simplify the llama.cpp stderr filter code 2025-06-06 22:25:13 -07:00
oobabooga 45f823ddf6 Print \n after the llama.cpp progress bar reaches 1.0 2025-06-06 22:23:34 -07:00
oobabooga d47c8eb956 Remove quotes from LLM-generated websearch query (closes #7045). 
Fix by @Quiet-Joker
 2025-06-05 06:57:59 -07:00
oobabooga 977ec801b7 Improve table colors in instruct mode 2025-06-05 06:33:45 -07:00
Hanusz Leszek 3829507d0f
Stop model during graceful shutdown (#7042) 2025-06-04 15:13:36 -03:00
oobabooga 3d676cd50f Optimize syntax highlighting 2025-06-04 11:02:04 -07:00
oobabooga 66a75c899a Improve the scrollbars in code blocks 2025-06-04 10:59:43 -07:00
oobabooga 9bd7359ffa Scroll the textarea into view when editing a message 2025-06-04 10:47:14 -07:00
oobabooga 93b3752cdf Revert "Remove the "Is typing..." yield by default" 
This reverts commit b30a73016d.
 2025-06-04 09:40:30 -07:00
oobabooga b38ec0ec38 Update llama.cpp 2025-06-02 11:33:17 -07:00
oobabooga b30a73016d Remove the "Is typing..." yield by default 2025-06-02 07:49:22 -07:00
oobabooga 7278548cd1
Simplify the one-click installer (#7039) 2025-06-02 09:57:55 -03:00
oobabooga bb409c926e
Update only the last message during streaming + add back dynamic UI update speed (#7038) 2025-06-02 09:50:17 -03:00
oobabooga 45c9ae312c Use the flash-attention wheels in https://github.com/kingbri1/flash-attention 2025-06-01 22:17:22 -07:00
oobabooga 2db7745cbd Show llama.cpp prompt processing on one line instead of many lines 2025-06-01 22:12:24 -07:00