Commit Graph

  • 5ae3038572
    Update server.py oobabooga 2023-04-18 01:37:54 -0300
  • 09b97e82e5
    Rename monkey_patch_gradio.py to dirty_patch_gradio.py oobabooga 2023-04-18 01:37:38 -0300
  • b069bb1f2e
    Update monkey_patch_gradio.py oobabooga 2023-04-18 01:32:42 -0300
  • 00186f76f4
    Monkey patch gradio to prevent it from calling home oobabooga 2023-04-18 01:13:16 -0300
  • 8819a799fb
    Update server.py oobabooga 2023-04-18 01:12:36 -0300
  • d03251bd8f
    Add files via upload oobabooga 2023-04-18 01:12:08 -0300
  • 07dfa42833 minor fix for training in not-4bit Alex "mcmonkey" Goodwin 2023-04-17 20:57:33 -0700
  • a7b7e412a6 add workaround for peft saving bug Alex "mcmonkey" Goodwin 2023-04-17 20:46:05 -0700
  • a4ee6018c5 add support for pip installable alpaca_lora_4bit and make the monkey patch usable for other 4bit model John Smith 2023-04-18 11:45:52 +0800
  • 2550628bfc initial experimental 4bit lora support Alex "mcmonkey" Goodwin 2023-04-17 20:18:48 -0700
  • 6a810b16b2
    typo in training.py (#1329) Tynan Burke 2023-04-17 18:40:46 -0600
  • 7293d47a17 reworked ui and added new axes options Clay Shoaf 2023-04-17 20:14:28 -0400
  • 6b07591bb3 Revert bc2d02a v0xie 2023-04-17 16:22:10 -0700
  • bc2d02a898 Correct api-example-stream custom_stopping_strings type v0xie 2023-04-17 16:10:55 -0700
  • 23c2663185 == should be = tynan 2023-04-17 16:59:20 -0600
  • ac2973ffc6 Add a warning for --share oobabooga 2023-04-17 19:34:28 -0300
  • ae81bc5677 Added custom_stopping_strings option to preset files Fire 2023-04-17 14:01:58 -0500
  • 0b24c3da1b Add Evaluation tab oobabooga 2023-04-17 15:34:45 -0300
  • 383656b7e6
    Merge branch 'oobabooga:main' into main ye7iaserag 2023-04-17 20:22:29 +0200
  • c544386824 Reset your name when choosing a character oobabooga 2023-04-17 13:56:40 -0300
  • 163ea295e7 Fix but in API extension oobabooga 2023-04-17 13:54:15 -0300
  • b1b9519539 Merge branch 'main' of github.com:oobabooga/text-generation-webui oobabooga 2023-04-17 13:52:49 -0300
  • c3dc348d1c Don't show 'None' in the LoRA list oobabooga 2023-04-17 13:52:23 -0300
  • fef73c7e4b Update google_translate extension: - now it save language settings - you have a choose between GoogleTranslator and LibreTranslator - you can set a custom url for LibreTranslator server (for example, for local LibreTranslator installation) Janvarev Vladislav 2023-04-17 19:09:10 +0300
  • 301c687c64
    Update README.md oobabooga 2023-04-17 11:25:26 -0300
  • 44949e393a
    Remove code brought in from merge conflict Brian O'Connor 2023-04-17 10:17:14 -0400
  • 704f4ec4cf
    Merge branch 'main' into chat-api Brian O'Connor 2023-04-17 10:15:34 -0400
  • 19e3a59997 Remove unused extension oobabooga 2023-04-17 11:06:08 -0300
  • 89bc540557 Update README oobabooga 2023-04-17 10:55:35 -0300
  • 07de7d0426
    Load llamacpp before quantized model (#1307) catalpaaa 2023-04-17 06:47:26 -0700
  • 3961f49524
    Add note about --no-fused_mlp ignoring --gpu-memory (#1301) practicaldreamer 2023-04-17 08:46:37 -0500
  • 56ff1d8f4f Fix TypeError in browser console on default mode DavG25 2023-04-17 14:14:20 +0200
  • b341b0ddb5 Update models.py catalpaaa 2023-04-17 04:03:48 -0700
  • 7ff2cc8316 Add support for stopping strings in RWKV models v0xie 2023-04-17 02:07:19 -0700
  • 0eac89a67a
    Add note about --no-fused_mlp practicaldreamer 2023-04-17 02:53:52 -0500
  • 0c5fff8332
    Add note about --no-fused_mlp ignoring --gpu-memory practicaldreamer 2023-04-17 02:50:58 -0500
  • b57ffc2ec9
    Update to support GPTQ triton commit c90adef (#1229) sgsdxzy 2023-04-17 12:11:18 +0800
  • 7d741dcf56 Add troubleshooting tips. Light 2023-04-17 11:50:20 +0800
  • 503622fac6 Merge remote-tracking branch 'origin/main' into triton Light 2023-04-17 11:38:41 +0800
  • 209fcd21d5 Reorganize Parameters tab oobabooga 2023-04-17 00:33:22 -0300
  • 3e5cdd005f
    Update README.md oobabooga 2023-04-16 23:28:59 -0300
  • 39099663a0
    Add 4-bit LoRA support (#1200) oobabooga 2023-04-16 23:26:52 -0300
  • a3229b428b Remove a space oobabooga 2023-04-16 23:25:29 -0300
  • ea79462488 Update README oobabooga 2023-04-16 23:16:15 -0300
  • 367fdd084c Add some comments oobabooga 2023-04-16 23:15:07 -0300
  • f665a634f9 Merge branch 'main' into 4bit-lora oobabooga 2023-04-16 23:06:04 -0300
  • 9311f8e95b Fix TypeError in browser console DavG25 2023-04-17 03:19:34 +0200
  • ec3e869c27 Merge branch 'main' of github.com:oobabooga/text-generation-webui oobabooga 2023-04-16 21:26:42 -0300
  • 46a8aa8c09 Readability oobabooga 2023-04-16 21:26:19 -0300
  • 5011f94659
    Improved compatibility between silero and sd_api_pictures (#1196) GuizzyQC 2023-04-16 20:18:52 -0400
  • 61d6f7f507
    Add dependencies to Dockerfile for TTS extensions (#1276) svupper 2023-04-17 02:17:00 +0200
  • 4cd2a9d824
    Bump transformers from 4.28.0 to 4.28.1 (#1288) dependabot[bot] 2023-04-16 21:12:57 -0300
  • 7dc2e39a88
    Bump transformers from 4.28.0 to 4.28.1 dependabot[bot] 2023-04-17 00:11:07 +0000
  • fbd4906090
    Bump gradio from 3.25 to 3.27.0 dependabot[bot] 2023-04-17 00:11:02 +0000
  • 705121161b
    Update README.md oobabooga 2023-04-16 20:03:03 -0300
  • 50c55a51fc
    Update README.md oobabooga 2023-04-16 19:22:31 -0300
  • c6fe1ced01
    Add ChatGLM support (#1256) Forkoz 2023-04-16 22:15:03 +0000
  • 6b1b183f4e Sort imports oobabooga 2023-04-16 19:12:20 -0300
  • cdaf421f77 Only allow trust_remote_code for ChatGLM oobabooga 2023-04-16 19:11:23 -0300
  • 3741e3f05e Add --trust-remote-code flag oobabooga 2023-04-16 19:04:43 -0300
  • a5d763ea91 Add file oobabooga 2023-04-16 18:52:01 -0300
  • f4d279ef96 Merge branch 'main' into Ph0rk0z-EasyChatGLM oobabooga 2023-04-16 18:51:11 -0300
  • 08d317ab8e Add ChatGLM template oobabooga 2023-04-16 18:49:22 -0300
  • 7693a5c2ef Fix the downloader script oobabooga 2023-04-16 18:31:18 -0300
  • 6a03ad0824 Remove fix_newlines() calls from chat.py oobabooga 2023-04-16 18:25:44 -0300
  • 5342f72968 Properly handle blockquote blocks oobabooga 2023-04-16 18:00:12 -0300
  • 27f3a78834 Better detect when no model is loaded oobabooga 2023-04-16 17:35:54 -0300
  • c8ad960018 Add defaults to the gradio API oobabooga 2023-04-16 17:33:28 -0300
  • c96529a1b3
    Update README.md oobabooga 2023-04-16 17:00:03 -0300
  • 6675f51ffe Change a color oobabooga 2023-04-16 16:48:20 -0300
  • beb95f5fe2 Add a style for the "chat" mode oobabooga 2023-04-16 16:44:50 -0300
  • cb95a2432c Add Koala support oobabooga 2023-04-16 14:40:45 -0300
  • b937c9d8c2
    Add skip_special_tokens checkbox for Dolly model (#1218) oobabooga 2023-04-16 14:24:49 -0300
  • 9a177b43d9 Fix a bug oobabooga 2023-04-16 14:22:07 -0300
  • 5153f1fb0d Reorder parameters oobabooga 2023-04-16 14:19:59 -0300
  • 6e43f30163 Handle ### End oobabooga 2023-04-16 13:43:31 -0300
  • f47f9084f9 Fix verbose output oobabooga 2023-04-16 13:24:38 -0300
  • a9c7ef4159 Exclude yaml files from model list oobabooga 2023-04-16 12:47:30 -0300
  • 89185de650 I added an audible notification after text generation. If there is a file "notification.mp3" in the root. HappyWorld 2023-04-16 18:45:12 +0300
  • 4e035cc3fb Fix api-example-stream oobabooga 2023-04-16 12:12:31 -0300
  • a64ed4ad83
    Update Dockerfile svupper 2023-04-16 16:26:58 +0200
  • 8cc07dac32 Merge remote-tracking branch 'origin/main' into triton Light 2023-04-16 16:51:05 +0800
  • b705b4210c Minor changes to training.py oobabooga 2023-04-16 03:08:37 -0300
  • d832d96e9d Add support for GPTQ-triton using the --gptq-triton flag. night 2023-04-15 22:46:48 -0700
  • 5c513a5f5c Make training.py more readable oobabooga 2023-04-16 02:46:27 -0300
  • a3eec62b50
    Lora trainer improvements part 3 (#1098) Alex "mcmonkey" Goodwin 2023-04-15 22:35:13 -0700
  • ac19d5101f
    revert incorrect eos_token_id change from #814 (#1261) kernyan 2023-04-16 00:47:01 -0400
  • a0a8accee3
    Merge branch 'oobabooga:main' into main kernyan 2023-04-16 00:43:49 -0400
  • d7ee19cdfd revert incorrect eos_token_id change from #814 kernyan 2023-04-16 00:43:02 -0400
  • a2127239de Fix a bug oobabooga 2023-04-16 01:41:37 -0300
  • 9d3c6d2dc3 Fix a bug oobabooga 2023-04-16 01:40:47 -0300
  • 7e598dc64f
    Many improvements to GuizzyQC 2023-04-16 00:38:15 -0400
  • 16a3a5b039
    Merge pull request from GHSA-hv5m-3rp9-xcpf Mikel Bober-Irizar 2023-04-16 05:36:50 +0100
  • 8cea1e9308
    Replaced the parsing library GuizzyQC 2023-04-16 00:36:30 -0400
  • d2ea925fa5 Bump llama-cpp-python to use LlamaCache oobabooga 2023-04-16 00:53:40 -0300
  • 2b107d09d0
    Update models.py to support chatGLM Forkoz 2023-04-15 20:31:55 -0500
  • 6edfd166b4
    Create requirements.txt GuizzyQC 2023-04-15 20:05:00 -0400
  • cb984fc841
    Create script.py GuizzyQC 2023-04-15 19:59:49 -0400
  • 12f1170dcf Put the config.yaml back da3dsoul 2023-04-15 19:41:22 -0400
  • 7d6f0b1f84
    Update gitignore. sd_api_pictures won't have wav da3dsoul 2023-04-15 19:37:11 -0400