text-generation-webui

mmarch/text-generation-webui

Fork 0

Commit graph

f740ee558c

Merge branch 'oobabooga:main' into lora-and-model-dir catalpaaa 2023-03-25 01:28:33 -07:00
ce9a5e3b53

Update install.bat jllllll 2023-03-25 02:22:02 -05:00
2e02d42682 Changed things around to allow Micromamba to work with paths containing spaces. jllllll 2023-03-25 01:14:29 -05:00
70f9565f37

Update README.md oobabooga 2023-03-25 02:35:30 -03:00
25be9698c7

Fix LoRA on mps oobabooga 2023-03-25 01:18:32 -03:00
3da633a497

Merge pull request #529 from EyeDeck/main oobabooga 2023-03-24 23:51:01 -03:00
1e260544cd

Update install.bat jllllll 2023-03-24 21:25:14 -05:00
d51cb8292b Update server.py catalpaaa 2023-03-24 17:36:31 -07:00
9e2963e0c8 Update server.py catalpaaa 2023-03-24 17:35:45 -07:00
ec2a1facee Update server.py catalpaaa 2023-03-24 17:34:33 -07:00
b37c54edcf lora-dir, model-dir and login auth catalpaaa 2023-03-24 17:30:18 -07:00
fa916aa1de

Update INSTRUCTIONS.txt jllllll 2023-03-24 18:28:46 -05:00
586775ad47

Update download-model.bat jllllll 2023-03-24 18:25:49 -05:00
bddbc2f898

Update start-webui.bat jllllll 2023-03-24 18:19:23 -05:00
2604e3f7ac

Update download-model.bat jllllll 2023-03-24 18:15:24 -05:00
24870e51ed

Update micromamba-cmd.bat jllllll 2023-03-24 18:12:02 -05:00
f0c82f06c3

Add files via upload jllllll 2023-03-24 18:09:44 -05:00
9fa47c0eed

Revert GPTQ_loader.py (accident) oobabooga 2023-03-24 19:57:12 -03:00
a6bf54739c

Revert models.py (accident) oobabooga 2023-03-24 19:56:45 -03:00
eec773b1f4

Update install.bat jllllll 2023-03-24 17:54:47 -05:00
0a16224451

Update GPTQ_loader.py oobabooga 2023-03-24 19:54:36 -03:00
a80aa65986

Update models.py oobabooga 2023-03-24 19:53:20 -03:00
817e6c681e

Update install.bat jllllll 2023-03-24 17:51:13 -05:00
a80a5465f2

Update install.bat jllllll 2023-03-24 17:27:29 -05:00
507db0929d

Do not use empty user messages in chat mode oobabooga 2023-03-24 17:22:22 -03:00
6e1b16c2aa

Update html_generator.py oobabooga 2023-03-24 17:18:27 -03:00
ffb0187e83

Update chat.py oobabooga 2023-03-24 17:17:29 -03:00
c14e598f14

Merge pull request #433 from mayaeary/fix/api-reload oobabooga 2023-03-24 16:56:10 -03:00
bfe960731f

Merge branch 'main' into fix/api-reload oobabooga 2023-03-24 16:54:41 -03:00
4a724ed22f

Reorder imports oobabooga 2023-03-24 16:53:56 -03:00
8fad84abc2

Update extensions.py oobabooga 2023-03-24 16:51:27 -03:00
d8e950d6bd

Don't load the model twice when using --lora oobabooga 2023-03-24 16:30:32 -03:00
fd99995b01

Make the Stop button more consistent in chat mode oobabooga 2023-03-24 15:59:27 -03:00
b740c5b284

Add display of context when input was generated Forkoz 2023-03-24 08:56:07 -05:00
4f5c2ce785

Fix chat_generation_attempts oobabooga 2023-03-24 02:03:30 -03:00
04417b658b

Update README.md oobabooga 2023-03-24 01:40:43 -03:00
bb4cb22453

Download .pt files using download-model.py (for 4-bit models) oobabooga 2023-03-24 00:49:04 -03:00
143b5b5edf

Mention one-click-bandaid in the README oobabooga 2023-03-23 23:28:50 -03:00
dcfd866402 Allow loading of .safetensors through GPTQ-for-LLaMa EyeDeck 2023-03-23 21:31:34 -04:00
8747c74339

Another missing import oobabooga 2023-03-23 22:19:01 -03:00
7078d168c3

Missing import oobabooga 2023-03-23 22:16:08 -03:00
d1327f99f9

Fix broken callbacks.py oobabooga 2023-03-23 22:12:24 -03:00
9bdb3c784d

Minor fix oobabooga 2023-03-23 22:02:40 -03:00
b0abb327d8

Update LoRA.py oobabooga 2023-03-23 22:02:09 -03:00
bf22d16ebc

Clear cache while switching LoRAs oobabooga 2023-03-23 21:56:26 -03:00
4578e88ffd

Stop the bot from talking for you in chat mode oobabooga 2023-03-23 21:38:20 -03:00
9bf6ecf9e2

Fix LoRA device map (attempt) oobabooga 2023-03-23 16:49:41 -03:00
c5ebcc5f7e

Change the default names (#518) oobabooga 2023-03-23 13:36:00 -03:00
483d173d23 Code reuse + indication Φφ 2023-03-21 20:19:38 +03:00
1917b15275 Unload and reload models on request Φφ 2023-03-21 13:15:42 +03:00
29bd41d453

Fix LoRA in CPU mode oobabooga 2023-03-23 01:05:13 -03:00
eac27f4f55

Make LoRAs work in 16-bit mode oobabooga 2023-03-23 00:55:33 -03:00
bfa81e105e

Fix FlexGen streaming oobabooga 2023-03-23 00:22:14 -03:00
7b6f85d327

Fix markdown headers in light mode oobabooga 2023-03-23 00:13:34 -03:00
de6a09dc7f

Properly separate the original prompt from the reply oobabooga 2023-03-23 00:12:40 -03:00
d5fc1bead7

Merge pull request #489 from Brawlence/ext-fixes oobabooga 2023-03-22 16:10:59 -03:00
bfb1be2820

Minor fix oobabooga 2023-03-22 16:09:48 -03:00
0abff499e2

Use image.thumbnail oobabooga 2023-03-22 16:03:05 -03:00
104212529f

Minor changes oobabooga 2023-03-22 15:55:03 -03:00
61346b88ea

Add "seed" menu in the Parameters tab wywywywy 2023-03-22 18:40:20 +00:00
5389fce8e1 Extensions performance & memory optimisations Φφ 2023-03-22 07:47:54 +03:00
45b7e53565

Only catch proper Exceptions in the text generation function oobabooga 2023-03-20 20:36:02 -03:00
6872ffd976

Update README.md oobabooga 2023-03-20 16:53:14 -03:00
db4219a340

Update comments oobabooga 2023-03-20 16:40:08 -03:00
7618f3fe8c

Add -gptq-preload for 4-bit offloading (#460) oobabooga 2023-03-20 16:30:56 -03:00
e96687b1d6 Do not send empty user input as part of the prompt. Vladimir Belitskiy 2023-03-20 14:16:48 -04:00
9a3bed50c3

Attempt at fixing 4-bit with CPU offload oobabooga 2023-03-20 15:11:56 -03:00
536d0a4d93

Add an import oobabooga 2023-03-20 14:00:40 -03:00
ca47e016b4

Do not display empty user messages in chat mode. Vladimir Belitskiy 2023-03-20 12:55:57 -04:00
75a7a84ef2

Exception handling (#454) oobabooga 2023-03-20 13:36:52 -03:00
a90f507abe

Exit elevenlabs_tts if streaming is enabled oobabooga 2023-03-20 11:49:42 -03:00
31ab2be8ef Remove redundant requirements #309 oobabooga 2023-03-19 22:10:55 -03:00
164e05daad Download .py files using download-model.py oobabooga 2023-03-19 20:34:52 -03:00
dd4374edde Update README oobabooga 2023-03-19 20:15:15 -03:00
9378754cc7 Update README oobabooga 2023-03-19 20:14:50 -03:00
7ddf6147ac

Update README.md oobabooga 2023-03-19 19:25:52 -03:00
b552d2b58a Remove unused imports o oobabooga 2023-03-19 19:24:41 -03:00
ddb62470e9 --no-cache and --gpu-memory in MiB for fine VRAM control oobabooga 2023-03-19 19:21:41 -03:00
4bafe45a51

Merge pull request #309 from Brawlence/main oobabooga 2023-03-19 13:24:47 -03:00
eab8de0d4a Merge branch 'main' into Brawlence-main oobabooga 2023-03-19 13:09:59 -03:00
4d701a6eb9 Create a mirror for the preset menu oobabooga 2023-03-19 12:51:47 -03:00
257edf5f56 Make the Default preset more reasonable oobabooga 2023-03-19 12:30:51 -03:00
a78b6508fc Make custom LoRAs work by default #385 oobabooga 2023-03-19 12:11:35 -03:00
7073e96093 Add back RWKV dependency #98 oobabooga 2023-03-19 12:05:28 -03:00
217e1d9fdf Merge branch 'main' of github.com:oobabooga/text-generation-webui oobabooga 2023-03-19 10:37:23 -03:00
c79fc69e95 Fix the API example with streaming #417 oobabooga 2023-03-19 10:36:57 -03:00
acdbd6b708 Check if app should display extensions ui Maya 2023-03-19 13:31:21 +00:00
81c9d130f2 Fix global Maya 2023-03-19 13:25:49 +00:00
099d7a844b Add setup method to extensions Maya 2023-03-19 13:22:24 +00:00
bd27353a08 Fix duplicating server on ui reload Maya 2023-03-19 12:51:27 +00:00
0cbe2dd7e9

Update README.md oobabooga 2023-03-18 12:24:54 -03:00
36ac7be76d

Merge pull request #407 from ThisIsPIRI/gitignore oobabooga 2023-03-18 11:57:10 -03:00
d2a7fac8ea

Use pip instead of conda for pytorch oobabooga 2023-03-18 11:56:04 -03:00
705f513c4c Add loras to .gitignore ThisIsPIRI 2023-03-18 23:33:24 +09:00
9ed3a03d4b

Don't use the official instructions oobabooga 2023-03-18 11:25:08 -03:00
a0b1a30fd5

Specify torchvision/torchaudio versions oobabooga 2023-03-18 11:23:56 -03:00
c753261338 Disable stop_at_newline by default oobabooga 2023-03-18 10:55:57 -03:00
7c945cfe8e Don't include PeftModel every time oobabooga 2023-03-18 10:55:24 -03:00
86b99006d9

Remove rwkv dependency oobabooga 2023-03-18 10:27:52 -03:00
a163807f86

Update README.md oobabooga 2023-03-18 03:07:27 -03:00