Commit Graph

  • 1dc2f8838d
    Merge branch 'main' of github.com:oobabooga/text-generation-webui loeken 2023-04-14 10:04:56 +0200
  • c119700aa1 Add defaults oobabooga 2023-04-14 01:59:39 -0300
  • 23264f1417 Minor bug fix oobabooga 2023-04-14 01:54:27 -0300
  • dea6684de5 Add a file oobabooga 2023-04-14 01:53:21 -0300
  • f5339e28e9 Add model-specific parameters oobabooga 2023-04-14 01:47:38 -0300
  • f1d0f5544c fixing repetition_penalty as well Regrant-Dev 2023-04-13 21:09:36 -0700
  • 4ed5152089 changing the params max_length to max_new_tokens to match the api documentation Regrant-Dev 2023-04-13 21:00:57 -0700
  • e1a6e31a60
    Merge branch 'oobabooga:main' into tortoise da3dsoul 2023-04-13 23:56:54 -0400
  • 57362f35e7
    Merge branch 'oobabooga:main' into main da3dsoul 2023-04-13 23:56:14 -0400
  • 2a400dc959 Tortoise TTS extension and install script da3dsoul 2023-04-13 23:53:02 -0400
  • 9d66957207
    Add --listen-host launch option (#1122) v0xie 2023-04-13 17:35:08 -0700
  • 403be8a27f
    Update README.md oobabooga 2023-04-13 21:23:35 -0300
  • 852a5aa13d
    Bump bitsandbytes from 0.37.2 to 0.38.1 (#1158) dependabot[bot] 2023-04-13 21:23:14 -0300
  • a71a3f32a2
    Bump bitsandbytes from 0.37.2 to 0.38.1 dependabot[bot] 2023-04-14 00:18:42 +0000
  • 84576a80d2
    Bump llama-cpp-python from 0.1.30 to 0.1.33 (#1157) dependabot[bot] 2023-04-13 21:17:59 -0300
  • 4d0d972dec
    Update requirements.txt oobabooga 2023-04-13 21:17:40 -0300
  • dd94561c86
    Bump llama-cpp-python from 0.1.30 to 0.1.33 dependabot[bot] 2023-04-14 00:09:15 +0000
  • 2908a51587 Settle for transformers 4.28.0 oobabooga 2023-04-13 21:07:00 -0300
  • 0143b92d5b initial multi-lora support Alex "mcmonkey" Goodwin 2023-04-13 17:01:34 -0700
  • 49cf6d4398 add higher_rank_limit option Alex "mcmonkey" Goodwin 2023-04-13 16:43:14 -0700
  • 5c099923fe Use suggested syntax for --listen_host option v0xie 2023-04-13 16:20:46 -0700
  • bf16872c90 Clone and import GPTQ-for-LLaMa if missing Leo Sternlicht 2023-04-13 15:22:06 -0400
  • aab2d66f1f Merge remote-tracking branch 'origin/main' into xyz Clay Shoaf 2023-04-13 12:33:33 -0400
  • c88ae609d2
    Merge branch 'main' of github.com:oobabooga/text-generation-webui loeken 2023-04-13 18:06:47 +0200
  • a959f74877
    Fixed generation for new main branch. innightwolfsleep 2023-04-13 22:03:21 +0600
  • 28a11f5724 Revert the Default preset to a previous version oobabooga 2023-04-13 12:59:18 -0300
  • a75e02de4d Simplify GPTQ_loader.py oobabooga 2023-04-13 12:13:07 -0300
  • c13e8651ad Suppress "TypedStorage is deprecated" warnings oobabooga 2023-04-13 12:09:42 -0300
  • 17ce7c8671 Suppress annoying bitsandbytes welcome message oobabooga 2023-04-13 12:04:39 -0300
  • ca293bb713 Show a warning if two quantized models are found oobabooga 2023-04-13 12:04:27 -0300
  • fbb448ce4f If only 1 model is available, load that model oobabooga 2023-04-13 11:44:10 -0300
  • 8b482b4127
    Merge #1073 from sgsdxzy/triton oobabooga 2023-04-13 11:31:21 -0300
  • fde6d06167 Prioritize names with the groupsize in them oobabooga 2023-04-13 11:27:03 -0300
  • f2bf1a2c9e Add some comments, remove obsolete code oobabooga 2023-04-13 11:17:32 -0300
  • 5744b31593 Reorganize some buttons oobabooga 2023-04-13 11:05:47 -0300
  • da74cd7c44 Generalized weight search path. Light 2023-04-13 21:43:32 +0800
  • 7a0ef1c941 Reorganize whisper extension oobabooga 2023-04-13 10:40:27 -0300
  • 02cf8f5898 Merge branch 'main' of github.com:oobabooga/text-generation-webui oobabooga 2023-04-13 10:35:43 -0300
  • 04866dc4fc Add a warning for when no model is loaded oobabooga 2023-04-13 10:35:08 -0300
  • 6e19ae4b2f
    Fix gpt-j model type in UI (#1129) Xan 2023-04-13 23:17:20 +1000
  • 97e67d136b Update README.md Light 2023-04-13 21:00:58 +0800
  • cf58058c33 Change warmup_autotune to a negative switch. Light 2023-04-13 20:59:49 +0800
  • 9d3928043d Merge remote-tracking branch 'origin/main' into xyz Clay Shoaf 2023-04-13 08:57:54 -0400
  • 295d9caa23 I don't know what I'm doing here Clay Shoaf 2023-04-13 08:53:30 -0400
  • bef6f3d1da Better way to sort the models/loras oobabooga 2023-04-12 22:56:32 -0300
  • a38f07ed4d Add --model-menu option oobabooga 2023-04-12 21:24:26 -0300
  • 2ca8f41f62 Add some labels oobabooga 2023-04-12 18:39:21 -0300
  • 4d90adb1e2 Update settings-template.json oobabooga 2023-04-12 18:30:43 -0300
  • d4e9364f10 Update a comment oobabooga 2023-04-12 18:26:15 -0300
  • 551fc9f7ea Add the GPU index to the label oobabooga 2023-04-12 18:24:19 -0300
  • 59b06fac02 Handle the no-GPU / multi-GPU cases oobabooga 2023-04-12 18:21:14 -0300
  • eca5a1a767 Link to developer.nvidia.com (#1104) MarlinMr 2023-04-12 20:56:42 +0200
  • 1394159a1a SD_api_pictures: Fix for metadata (#1082) Φφ 2023-04-12 17:42:30 +0300
  • 783e78acfd lora training fixes: (#970) Lukas 2023-04-12 16:38:01 +0200
  • f2fd0b0e3c Add model settings to the Models tab oobabooga 2023-04-12 17:09:56 -0300
  • 17f3c005c1 Simplify send_pictures oobabooga 2023-04-12 10:30:12 -0300
  • 1533658138 Fix send_pictures extension oobabooga 2023-04-12 10:27:06 -0300
  • 17f80fa0c9 Fix silero_tts oobabooga 2023-04-12 00:58:11 -0300
  • 0442463f6e Make api-example-stream.py functional again oobabooga 2023-04-12 00:25:30 -0300
  • 5d352bacf3 Change fn_index in api_example_stream (#904) Andy Salerno 2023-04-11 20:15:12 -0700
  • b5e9760efe Mention that pull request reviews are welcome oobabooga 2023-04-11 23:12:48 -0300
  • fab56fdd22 API: add endpoint for counting tokens (#1051) Tymec 2023-04-12 04:08:42 +0200
  • b0212a2184 Add missing new parameters to API extension Alexander01998 2023-04-12 03:41:13 +0200
  • 8356663757 Update API example oobabooga 2023-04-11 22:43:23 -0300
  • 67f19756bc Comment lines that were causing undefined behavior oobabooga 2023-04-11 22:40:04 -0300
  • 7319f58183 Add send dummy message/reply buttons oobabooga 2023-04-11 22:21:41 -0300
  • e05e44d751 Fix Continue in chat mode oobabooga 2023-04-11 21:46:17 -0300
  • 5c02ddf1a1 Auto-scroll to the bottom when streaming is over in notebook/default modes oobabooga 2023-04-11 20:58:10 -0300
  • 45033f8dde More reasonable default preset oobabooga 2023-04-11 18:57:46 -0300
  • 407763e0b9 Two new options: truncation length and ban eos token oobabooga 2023-04-11 18:46:06 -0300
  • 8386c1d0c9 Update README.md oobabooga 2023-04-11 14:42:10 -0300
  • e43bc94819 Fix text overflow in chat and instruct mode (#1044) DavG25 2023-04-11 19:41:29 +0200
  • 69580d63b4 Update the API extension oobabooga 2023-04-11 13:06:51 -0300
  • d664f65099 Update the API example oobabooga 2023-04-11 12:57:36 -0300
  • 9d8d4e045c allow custom stopping strings in all modes (#903) catalpaaa 2023-04-11 08:30:06 -0700
  • b42d185031 Refactor the UI oobabooga 2023-04-11 11:46:30 -0300
  • 15d5a043f2 Merge remote-tracking branch 'origin/main' into triton Light 2023-04-13 19:38:51 +0800
  • 9485fa2c9e Fix gpt-j model type in UI Xan 2023-04-13 18:35:02 +1000
  • 5484c51569 Add --listen-host option v0xie 2023-04-12 22:31:47 -0700
  • 3624b9f4af
    Merge branch 'main' into patch-1 Alexander Dibrov 2023-04-12 22:33:40 -0500
  • ddbd237ec9 Better way to sort the models/loras oobabooga 2023-04-12 22:56:32 -0300
  • 65ec2b7340 remove gptq_bits ref as main branch removed that setting Alex "mcmonkey" Goodwin 2023-04-12 18:32:47 -0700
  • 4773a12bde add nbatch option for llama.cpp eiery 2023-04-12 21:05:52 -0400
  • 7dfbe54f42 Add --model-menu option oobabooga 2023-04-12 21:24:26 -0300
  • 86c10c6f0c Add some labels oobabooga 2023-04-12 18:39:21 -0300
  • 388038fb8e Update settings-template.json oobabooga 2023-04-12 18:30:43 -0300
  • 0baa50bcc4 Update a comment oobabooga 2023-04-12 18:26:15 -0300
  • 5d1d0bd11f Add the GPU index to the label oobabooga 2023-04-12 18:24:19 -0300
  • 13789fd200 Handle the no-GPU / multi-GPU cases oobabooga 2023-04-12 18:21:14 -0300
  • 527ac07fdf Fix Chat mode vs mode in Coqui, as was done to Silero da3dsoul 2023-04-12 16:50:17 -0400
  • 8f08d1f953 Coqui AI TTS normalization. Extract the normalization into core for reuse da3dsoul 2023-04-12 16:29:25 -0400
  • c7ff81724a Coqui TTS da3dsoul 2023-04-08 16:46:39 -0400
  • 10e939c9b4 Merge branch 'main' of github.com:oobabooga/text-generation-webui oobabooga 2023-04-12 17:21:59 -0300
  • 1566d8e344 Add model settings to the Models tab oobabooga 2023-04-12 17:09:56 -0300
  • 47daf891fe
    Link to developer.nvidia.com (#1104) MarlinMr 2023-04-12 20:56:42 +0200
  • 8d511f47bc Link to developer.nvidia.com MarlinMr 2023-04-12 20:44:47 +0200
  • 1d29e32de5
    Remove debug code ye7iaserag 2023-04-12 20:19:46 +0200
  • a405064ceb Better dispatch. Light 2023-04-13 01:48:17 +0800
  • 467cfab185
    Merge pull request #8 from innightwolfsleep/innightwolfsleep-patch-6 innightwolfsleep 2023-04-12 23:38:14 +0600
  • 3524bb5730
    Added impersonate, history, thread lock innightwolfsleep 2023-04-12 23:37:32 +0600