Commit graph

Select branches

Hide pull requests

main

Mono Color

• 625d81f495
  Update character log logic (#977) Brian O'Connor 2023-04-09 21:20:21 -04:00
• 57f768eaad Better preset in api-example.py oobabooga 2023-04-09 22:18:40 -03:00
• a3085dba07 Fix LlamaTokenizer eos_token (attempt) oobabooga 2023-04-09 21:19:39 -03:00
• 120f5662cf Better handle spaces for Continue oobabooga 2023-04-09 20:37:31 -03:00
• b27d757fd1 Minor change oobabooga 2023-04-09 20:06:20 -03:00
• d29f4624e9 Add a Continue button to chat mode oobabooga 2023-04-09 20:04:16 -03:00
• 170e0c05c4 Typo oobabooga 2023-04-09 17:00:59 -03:00
• 34ec02d41d Make download-model.py importable oobabooga 2023-04-09 16:59:59 -03:00
• f91d3a3ff4 server.py readability oobabooga 2023-04-09 14:46:32 -03:00
• ebdf4c8c12 path fixed Usama Kenway 2023-04-09 16:53:21 +05:00
• 7436dd5b4a download custom model menu (from hugging face) added in model tab Usama Kenway 2023-04-09 16:11:43 +05:00
• bce1b7fbb2
  Update README.md oobabooga 2023-04-09 02:19:40 -03:00
• f7860ce192
  Update README.md oobabooga 2023-04-09 02:19:17 -03:00
• ece8ed2c84
  Update README.md oobabooga 2023-04-09 02:18:42 -03:00
• cc693a7546 Remove obsolete code oobabooga 2023-04-09 00:51:07 -03:00
• 0818bc93ad Add working llamaa-cpp-python install from wheel. Lou Bernardi 2023-04-08 22:44:55 -04:00
• 2fde50a800
  Delete docker.md oobabooga 2023-04-08 22:37:54 -03:00
• acc235aced
  updated docs for docker, setup video added, removed left over GPTQ_VERSION from docker-compose (#940) loeken 2023-04-09 03:35:15 +02:00
• df561fd896
  Fix ggml downloading in download-model.py (#915) Blake Wyatt 2023-04-08 21:52:30 +00:00
• d272ac46dd Add Pillow as a requirement oobabooga 2023-04-08 18:48:46 -03:00
• cb169d0834 Minor formatting changes oobabooga 2023-04-08 17:34:07 -03:00
• 2f16d0afca Remove redundant events oobabooga 2023-04-08 17:32:36 -03:00
• a6a00cb82f
  Properly concatenate chat events oobabooga 2023-04-08 17:25:21 -03:00
• c97c270040
  Send_pictures small fix (#546) Φφ 2023-04-08 07:55:16 +03:00
• 0b458bf82d Simplify a function oobabooga 2023-04-07 21:37:41 -03:00
• ffd102e5c0
  SD Api Pics extension, v.1.1 (#596) Φφ 2023-04-08 03:36:04 +03:00
• 5543a5089d Auto-submit the whisper extension transcription oobabooga 2023-04-07 15:57:29 -03:00
• 1dc464dcb0 Sort imports oobabooga 2023-04-07 14:42:03 -03:00
• 962e33dc10 Change button style oobabooga 2023-04-07 12:22:14 -03:00
• 42ea6a3fc0 Change the timing for setup() calls oobabooga 2023-04-07 12:20:57 -03:00
• e563b015d8
  Silero TTS offline cache (#628) Φφ 2023-04-07 18:15:57 +03:00
• 1c413ed593 Remove torch from silero oobabooga 2023-04-07 11:51:50 -03:00
• 3f922d4bfb
  Extract the Preprocessing for Silero into a file and Improve it (#757) da3dsoul 2023-04-07 10:46:29 -04:00
• 744bf7cbf2
  Get rid of type parameter warning (#883) Maya 2023-04-07 17:17:16 +03:00
• 768354239b Change training file encoding oobabooga 2023-04-07 11:15:52 -03:00
• 6762e62a40 Simplifications oobabooga 2023-04-07 11:14:32 -03:00
• a453d4e9c4 Reorganize some chat functions oobabooga 2023-04-07 11:07:03 -03:00
• ec979cd9c4
  Use updated docker compose (#877) MarlinMr 2023-04-07 15:48:47 +02:00
• 2c0018d946
  Cosmetic change of README.md (#878) MarlinMr 2023-04-07 15:47:10 +02:00
• 8fa182cfa7
  Fix regeneration of first message in instruct mode (#881) Maya 2023-04-07 16:45:42 +03:00
• 862aad637b
  Tweak COPY order in Dockerfile (#863) Alastair D'Silva 2023-04-07 13:56:44 +10:00
• 46c4654226 More PEP8 stuff oobabooga 2023-04-07 00:52:02 -03:00
• ea6e77df72
  Make the code more like PEP8 for readability (#862) oobabooga 2023-04-07 00:15:45 -03:00
• 848c4edfd5
  Update README.md oobabooga 2023-04-06 22:52:35 -03:00
• e047cd1def Update README oobabooga 2023-04-06 22:50:58 -03:00
• 08b9d1b23a
  creating a layer with Docker/docker-compose (#633) loeken 2023-04-07 03:46:04 +02:00
• 64bcde56ab Minor css change oobabooga 2023-04-06 20:14:29 -03:00
• 58ed87e5d9
  Update requirements.txt oobabooga 2023-04-06 18:42:54 -03:00
• 21be80242e
  Bump rwkv from 0.7.2 to 0.7.3 (#842) dependabot[bot] 2023-04-06 17:52:27 -03:00
• 310bf46a94
  Instruction Character Vicuna, Instruction Mode Bugfix (#838) OWKenobi 2023-04-06 22:40:44 +02:00
• 20b8ca4482
  Add CSS for lists (#833) DavG25 2023-04-06 21:15:04 +02:00
• 113f94b61e Bump transformers (16-bit llama must be reconverted/redownloaded) oobabooga 2023-04-06 16:04:03 -03:00
• 5f4f38ca5d Merge branch 'main' of github.com:oobabooga/text-generation-webui oobabooga 2023-04-06 14:38:29 -03:00
• ef0f748618
  Prevent CPU version of Torch from being installed (#10 from jllllll/oobabooga-windows) oobabooga 2023-04-06 13:54:14 -03:00
• d9e7aba714
  Update README.md oobabooga 2023-04-06 13:42:24 -03:00
• 59058576b5 Remove unused requirement oobabooga 2023-04-06 13:28:21 -03:00
• eec3665845
  Add instructions for updating requirements oobabooga 2023-04-06 13:24:01 -03:00
• 03cb44fc8c Add new llama.cpp library (2048 context, temperature, etc now work) oobabooga 2023-04-06 13:12:14 -03:00
• 39f3fec913
  Broaden GPTQ-for-LLaMA branch support (#820) EyeDeck 2023-04-06 11:16:48 -04:00
• 8cd899515e Change instruct html a bit oobabooga 2023-04-06 12:00:20 -03:00
• 4a28f39823
  Update README.md oobabooga 2023-04-06 02:47:27 -03:00
• 158ec51ae3 Increase instruct mode padding oobabooga 2023-04-06 02:20:52 -03:00
• 0c7ef26981
  Lora trainer improvements (#763) Alex "mcmonkey" Goodwin 2023-04-05 22:04:11 -07:00
• 5b301d9a02 Create a Model tab oobabooga 2023-04-06 01:54:05 -03:00
• 4a400320dd Clean up oobabooga 2023-04-06 01:47:00 -03:00
• e94ab5dac1 Minor fixes oobabooga 2023-04-06 01:43:10 -03:00
• 641646a801
  Fix crash if missing instructions directory (#812) Randell Miller 2023-04-05 23:24:22 -05:00
• 3f3e42e26c
  Refactor several function calls and the API oobabooga 2023-04-06 01:22:15 -03:00
• 378d21e80c
  Add LLaMA-Precise preset (#767) SDS 2023-04-05 23:52:36 +02:00
• 1e656bef25
  Specifically target cuda 11.7 ver. of torch 2.0.0 jllllll 2023-04-05 16:52:05 -05:00
• 19b516b11b
  fix link to streaming api example (#803) eiery 2023-04-05 13:50:23 -04:00
• 7617ed5bfd
  Add AMD instructions oobabooga 2023-04-05 14:42:58 -03:00
• 770ef5744f Update README oobabooga 2023-04-05 14:38:11 -03:00
• 8203ce0cac
  Stop character pic from being cached when changing chars or clearing. (#798) Forkoz 2023-04-05 12:25:01 -05:00
• 7f66421369 Fix loading characters oobabooga 2023-04-05 14:22:32 -03:00
• 90141bc1a8 Fix saving prompts on Windows oobabooga 2023-04-05 14:08:54 -03:00
• cf2c4e740b Disable gradio analytics globally oobabooga 2023-04-05 14:05:50 -03:00
• e722c240af Add Instruct mode oobabooga 2023-04-05 11:49:59 -03:00
• 3d6cb5ed63 Minor rewrite oobabooga 2023-04-05 01:21:40 -03:00
• f3a2e0b8a9 Disable pre_layer when the model type is not llama oobabooga 2023-04-05 01:19:26 -03:00
• ca8bb38949 Simplify gallery oobabooga 2023-04-05 00:34:17 -03:00
• 4ab679480e
  allow quantized model to be loaded from model dir (#760) catalpaaa 2023-04-04 19:19:38 -07:00
• ae1fe45bc0 One more cache reset oobabooga 2023-04-04 23:15:57 -03:00
• 8ef89730a5 Try to better handle browser image cache oobabooga 2023-04-04 23:09:28 -03:00
• cc6c7a37f3 Add make_thumbnail function oobabooga 2023-04-04 23:03:58 -03:00
• 80dfba05f3 Better crop/resize cached images oobabooga 2023-04-04 22:52:15 -03:00
• 65d8a24a6d Show profile pictures in the Character tab oobabooga 2023-04-04 22:28:49 -03:00
• f70a2e3ad4
  Second attempt at fixing empty space oobabooga 2023-04-04 18:30:34 -03:00
• 9c86acda67
  Fix huge empty space in the Character tab oobabooga 2023-04-04 18:07:34 -03:00
• 38afc2470c
  Change indentation oobabooga 2023-04-04 16:32:27 -03:00
• b2ce7282a1
  Use past transformers version #773 oobabooga 2023-04-04 16:11:42 -03:00
• 5aaf771c7d
  Add additional sanity check jllllll 2023-04-04 12:31:26 -05:00
• ee4547cd34
  Detect "vicuna" as llama model type (#772) OWKenobi 2023-04-04 18:23:27 +02:00
• 881dbc3d44
  Add back the name oobabooga 2023-04-04 13:11:34 -03:00
• af0cb283e4
  improve the example character yaml format (#770 from mcmonkey4eva) oobabooga 2023-04-04 12:52:21 -03:00
• 165d757444 improve the example character yaml format - use multiline blocks Alex "mcmonkey" Goodwin 2023-04-04 08:25:11 -07:00
• 8de22ac82a Merge character upload tabs oobabooga 2023-04-03 18:01:45 -03:00
• b24147c7ca Document --pre_layer oobabooga 2023-04-03 17:34:25 -03:00
• 4c9ed09270 Update settings template oobabooga 2023-04-03 14:59:26 -03:00
• ad37f396fc
  Bump rwkv from 0.7.1 to 0.7.2 (#747) dependabot[bot] 2023-04-03 14:29:57 -03:00