mmarch/text-generation-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Commit graph

  • 74bf2f05b1
         Update llama.cpp-models.md oobabooga 2023-06-01 11:58:33 -03:00
  • 90dc8a91ae
         Update llama.cpp-models.md oobabooga 2023-06-01 11:57:57 -03:00
  • aba56de41b
         Update README.md oobabooga 2023-06-01 11:46:28 -03:00
  • c9ac45d4cf
         Update Using-LoRAs.md oobabooga 2023-06-01 11:34:04 -03:00
  • 9aad6d07de
         Update Using-LoRAs.md oobabooga 2023-06-01 11:32:41 -03:00
  • df18ae7d6c
         Update README.md oobabooga 2023-06-01 11:27:33 -03:00
  • 248ef32358 Print a big message for CPU users oobabooga 2023-06-01 01:38:48 -03:00
  • 290a3374e4 Don't download a model during installation oobabooga 2023-06-01 01:20:56 -03:00
  • e52b43c934
         Update GPTQ-models-(4-bit-mode).md oobabooga 2023-06-01 01:17:13 -03:00
  • 1aed2b9e52
         Make it possible to download protected HF models from the command line. (#2408) Morgan Schweers 2023-05-31 20:11:21 -07:00
  • 419c34eca4
         Update GPTQ-models-(4-bit-mode).md oobabooga 2023-05-31 23:49:00 -03:00
  • 486ddd62df Add tfs and top_a to the API examples oobabooga 2023-05-31 23:44:38 -03:00
  • b6c407f51d Don't stream at more than 24 fps oobabooga 2023-05-31 23:41:42 -03:00
  • a160230893 Update GPTQ-models-(4-bit-mode).md oobabooga 2023-05-31 23:38:15 -03:00
  • 2cdf525d3b Bump llama-cpp-python version oobabooga 2023-05-31 23:29:02 -03:00
  • 2e53caa806
         Create LICENSE oobabooga 2023-05-31 16:28:36 -03:00
  • dea1bf3d04
         Parse g++ version instead of using string matching (#72) Sam 2023-05-31 13:44:36 -04:00
  • 97bc7e3fb6
         Adds functionality for user to set flags via environment variable (#59) gavin660 2023-05-31 10:43:22 -07:00
  • 5405635305
         Install pre-compiled wheels for Linux (#74) Sam 2023-05-31 13:41:54 -04:00
  • be98e74337
         Install older bitsandbytes on older gpus + fix llama-cpp-python issue (#75) jllllll 2023-05-31 12:41:03 -05:00
  • 412e7a6a96
         Update README.md to include missing flags (#2449) jllllll 2023-05-31 09:07:56 -05:00
  • 6627f7feb9
         Add notice about downgrading gcc and g++ (#2446) AlpinDale 2023-05-31 05:58:53 +04:30
  • bfbd13ae89
         Update docker repo link (#2340) Atinoda 2023-05-31 02:14:49 +01:00
  • a6d3f010a5
         extensions/openai: include all available models in Model.list (#2368) matatonic 2023-05-30 21:13:37 -04:00
  • e5b756ecfe
         Fixes #2331, IndexError: string index out of range (#2383) matatonic 2023-05-30 21:07:40 -04:00
  • b984a44f47
         fix error when downloading a model for the first time (#2404) Juan M Uys 2023-05-31 02:07:12 +01:00
  • 4715123f55
         Add a /api/v1/stop-stream API that allows the user to interrupt the generation (#2392) Yiximail 2023-05-31 09:03:40 +08:00
  • ebcadc0042
         extensions/openai: cross_origin + chunked_response (updated fix) (#2423) matatonic 2023-05-30 20:54:24 -04:00
  • df50f077db
         fixup missing tfs top_a params, defaults reorg (#2443) matatonic 2023-05-30 20:52:33 -04:00
  • 9ab90d8b60
         Fix warning for qlora (#2438) Forkoz 2023-05-30 09:09:18 -05:00
  • 0db4e191bd
         Improve chat buttons on mobile devices oobabooga 2023-05-30 00:30:15 -03:00
  • 3209440b7c
         Rearrange chat buttons oobabooga 2023-05-30 00:17:31 -03:00
  • 3578dd3611
         Change a warning message oobabooga 2023-05-29 22:40:54 -03:00
  • 3a6e194bc7
         Change a warning message oobabooga 2023-05-29 22:39:23 -03:00
  • e763ace593
         Update GPTQ-models-(4-bit-mode).md oobabooga 2023-05-29 22:35:49 -03:00
  • 86ef695d37
         Update GPTQ-models-(4-bit-mode).md oobabooga 2023-05-29 22:20:55 -03:00
  • 8e0a997c60
         Add new parameters to API extension oobabooga 2023-05-29 22:03:08 -03:00
  • 9e7204bef4
         Add tail-free and top-a sampling (#2357) Luis Lopez 2023-05-30 08:40:01 +08:00
  • b4662bf4af
         Download gptq_model*.py using download-model.py oobabooga 2023-05-29 16:12:54 -03:00
  • 540a161a08
         Update GPTQ-models-(4-bit-mode).md oobabooga 2023-05-29 15:45:40 -03:00
  • b8d2f6d876 Merge remote-tracking branch 'refs/remotes/origin/main' oobabooga 2023-05-29 15:33:05 -03:00
  • 1394f44e14 Add triton checkbox for AutoGPTQ oobabooga 2023-05-29 15:32:45 -03:00
  • 166a0d9893
         Update GPTQ-models-(4-bit-mode).md oobabooga 2023-05-29 15:07:59 -03:00
  • 962d05ca7e
         Update README.md oobabooga 2023-05-29 14:56:55 -03:00
  • 4a190a98fd
         Update GPTQ-models-(4-bit-mode).md oobabooga 2023-05-29 14:56:05 -03:00
  • 2b7ba9586f
         Fixes #2326, KeyError: 'assistant' (#2382) matatonic 2023-05-29 13:19:57 -04:00
  • 6de727c524 Improve Eta Sampling preset oobabooga 2023-05-29 13:56:15 -03:00
  • f34d20922c Minor fix oobabooga 2023-05-29 13:31:17 -03:00
  • 983eef1e29 Attempt at evaluating falcon perplexity (failed) oobabooga 2023-05-29 13:28:25 -03:00
  • 204731952a
         Falcon support (trust-remote-code and autogptq checkboxes) (#2367) Honkware 2023-05-29 08:20:18 -05:00
  • 60ae80cf28
         Fix hang in tokenizer for AutoGPTQ llama models. (#2399) Forkoz 2023-05-28 21:10:10 -05:00
  • 2f811b1bdf Change a warning message oobabooga 2023-05-28 22:48:20 -03:00
  • 9ee1e37121 Fix return message when no model is loaded oobabooga 2023-05-28 22:46:32 -03:00
  • f27135bdd3 Add Eta Sampling preset oobabooga 2023-05-28 22:42:43 -03:00
  • 00ebea0b2a Use YAML for presets and settings oobabooga 2023-05-28 22:34:12 -03:00
  • 2cf711f35e
         update SpeechRecognition dependency (#2345) Elias Vincent Simon 2023-05-26 05:34:57 +02:00
  • 78dbec4c4e
         Add 'scipy' to requirements.txt #2335 (#2343) jllllll 2023-05-25 21:26:25 -05:00
  • 0dbc3d9b2c
         Fix get_documents_ids_distances return error when n_results = 0 (#2347) Luis Lopez 2023-05-26 10:25:36 +08:00
  • 07a4f0569f
         Update README.md to account for BnB Windows wheel (#2341) jllllll 2023-05-25 16:44:26 -05:00
  • acfd876f29 Some qol changes to "Perplexity evaluation" oobabooga 2023-05-25 15:06:22 -03:00
  • 8efdc01ffb Better default for compute_dtype oobabooga 2023-05-25 15:05:53 -03:00
  • fc33216477 Small fix for n_ctx in llama.cpp oobabooga 2023-05-25 13:55:51 -03:00
  • 35009c32f0 Beautify all CSS oobabooga 2023-05-25 13:12:34 -03:00
  • 231305d0f5
         Update README.md oobabooga 2023-05-25 12:05:08 -03:00
  • 37d4ad012b Add a button for rendering markdown for any model oobabooga 2023-05-25 11:59:27 -03:00
  • 9a43656a50
         Add bitsandbytes note oobabooga 2023-05-25 11:21:52 -03:00
  • b1b3bb6923
         Improve environment isolation (#68) jllllll 2023-05-25 09:15:05 -05:00
  • c8ce2e777b
         Add instructions for CPU mode users oobabooga 2023-05-25 10:57:52 -03:00
  • 996c49daa7
         Remove bitsandbytes installation step oobabooga 2023-05-25 10:50:20 -03:00
  • 548f05e106 Add windows bitsandbytes wheel by jllllll oobabooga 2023-05-25 10:48:22 -03:00
  • cf088566f8
         Make llama.cpp read prompt size and seed from settings (#2299) DGdev91 2023-05-25 15:29:31 +02:00
  • ee674afa50
         Add superbooga time weighted history retrieval (#2080) Luis Lopez 2023-05-25 21:22:45 +08:00
  • a04266161d
         Update README.md oobabooga 2023-05-25 01:23:46 -03:00
  • 361451ba60
         Add --load-in-4bit parameter (#2320) oobabooga 2023-05-25 01:14:13 -03:00
  • 63ce5f9c28 Add back a missing bos token oobabooga 2023-05-24 13:54:36 -03:00
  • 3cd7c5bdd0
         LoRA Trainer: train_only_after option to control which part of your input to train on (#2315) Alex "mcmonkey" Goodwin 2023-05-24 08:43:22 -07:00
  • 9967e08b1f
         update llama-cpp-python to v0.1.53 for ggml v3, fixes #2245 (#2264) eiery 2023-05-24 09:25:28 -04:00
  • e50ade438a
         FIX silero_tts/elevenlabs_tts activation/deactivation (#2313) Gabriel Terrien 2023-05-24 15:06:38 +02:00
  • fc116711b0
         FIX save_model_settings function to also update shared.model_config (#2282) Gabriel Terrien 2023-05-24 15:01:07 +02:00
  • d37a28730d
         Beginning of multi-user support (#2262) flurb18 2023-05-24 08:38:20 -04:00
  • 7dc87984a2
         Fix spelling mistake in new name var of chat api (#2309) Anthony K 2023-05-23 21:03:03 -05:00
  • 1490c0af68 Remove RWKV from requirements.txt oobabooga 2023-05-23 20:48:12 -03:00
  • 7aed53559a
         Support of the --gradio-auth flag (#2283) Gabriel Terrien 2023-05-24 01:39:26 +02:00
  • 4155aaa96a
         Add mention to alternative docker repository (#2145) Atinoda 2023-05-24 00:35:53 +01:00
  • 9714072692
         [extensions/openai] use instruction templates with chat_completions (#2291) matatonic 2023-05-23 18:58:41 -04:00
  • 74aae34beb Allow passing your name to the chat API oobabooga 2023-05-23 18:41:58 -03:00
  • fb6a00f4e5 Small AutoGPTQ fix oobabooga 2023-05-23 15:20:01 -03:00
  • c2d2ef7c13
         Update Generation-parameters.md oobabooga 2023-05-23 02:11:28 -03:00
  • b0845ae4e8
         Update RWKV-model.md oobabooga 2023-05-23 02:10:08 -03:00
  • cd3618d7fb Add support for RWKV in Hugging Face format oobabooga 2023-05-23 02:07:28 -03:00
  • 75adc110d4 Fix "perplexity evaluation" progress messages oobabooga 2023-05-23 01:54:52 -03:00
  • 4d94a111d4 memoize load_character to speed up the chat API oobabooga 2023-05-23 00:50:58 -03:00
  • 8b9ba3d7b4 Fix a typo oobabooga 2023-05-22 20:13:03 -03:00
  • 0f51b64bb3
         Add a "dark_theme" option to settings.json (#2288) Gabriel Terrien 2023-05-23 00:45:11 +02:00
  • c5446ae0e2 Fix a link oobabooga 2023-05-22 19:38:34 -03:00
  • c0fd7f3257
         Add mirostat parameters for llama.cpp (#2287) oobabooga 2023-05-22 19:37:24 -03:00
  • ec7437f00a
         Better way to toggle light/dark mode oobabooga 2023-05-22 03:19:01 -03:00
  • d46f5a58a3 Add a button for toggling dark/light mode oobabooga 2023-05-22 03:11:44 -03:00
  • baf75356d4
         Bump transformers from 4.29.1 to 4.29.2 (#2268) dependabot[bot] 2023-05-22 02:50:18 -03:00
  • 4372eb228c Increase the interface area by 10px oobabooga 2023-05-22 00:55:33 -03:00