rixty/KoboldAI-Client
1
1
Fork 0
mirror of https://github.com/KoboldAI/KoboldAI-Client.git synced 2025-06-05 21:59:24 +02:00
Code Issues Projects Releases Wiki Activity

Commit Graph

  • f72ceeadd0 Cap transformers version henk717 2022-12-02 01:10:59 +01:00
  • 04d9172fcd Merge pull request #180 from VE-FORBRYDERNE/patch henk717 2022-11-21 20:02:14 +01:00
  • 9a3f0eaab2 Only enable TPU transpose optimization if loading from HF model vfbd 2022-11-21 13:47:18 -05:00
  • f2077b8e58 Merge pull request #179 from henk717/united 1.19.2 henk717 2022-11-20 16:26:03 +01:00
  • 2603f1fd5d Version bump Henk 2022-11-20 16:22:33 +01:00
  • 3084552c05 Sampler Order Fix for Models Henk 2022-11-14 17:15:39 +01:00
  • 13dff68de8 Sampler Order Loading Fix Henk 2022-11-14 16:59:53 +01:00
  • a66e1443fd New Models Henk 2022-11-12 16:54:40 +01:00
  • 440c5c333e Clear flask_session on launch Henk 2022-11-12 15:43:06 +01:00
  • f1e4664d56 Dependency improvements Henk 2022-11-11 21:13:51 +01:00
  • eb52ebd082 Merge branch 'main' into united Henk 2022-11-03 00:22:30 +01:00
  • 09b5ffc09d Merge pull request #175 from VE-FORBRYDERNE/gptj-patch henk717 2022-11-03 00:13:50 +01:00
  • b20d80ca2a Add vocab padding to embedding bias in gptj.json vfbd 2022-11-02 19:02:09 -04:00
  • 2e3a80b8ea Merge branch 'KoboldAI:main' into united henk717 2022-10-26 23:11:26 +02:00
  • 7b5a766b4a Merge pull request #172 from VE-FORBRYDERNE/accelerate-patch henk717 2022-10-26 22:42:05 +02:00
  • 3233e78c56 Fix "is on the meta device" error when loading model with disk cache vfbd 2022-10-26 16:00:45 -04:00
  • 442a9760b8 Hide V2 Saves Henk 2022-10-23 19:03:18 +02:00
  • 2300fb46ff Merge branch 'KoboldAI:main' into united henk717 2022-10-23 18:29:28 +02:00
  • 8ee795055c Force compatible HF Hub Henk 2022-10-23 18:28:50 +02:00
  • ea8b50d31e Conda fix for update script Henk 2022-10-23 16:00:18 +02:00
  • 0da404d4f8 Conda conflict fix Henk 2022-10-23 14:10:44 +02:00
  • 4699ded3ce Tuner Dependencies Henk 2022-10-22 19:00:06 +02:00
  • 351fb3c80b Merge pull request #232 from VE-FORBRYDERNE/mkultra henk717 2022-10-22 14:13:42 +02:00
  • 10a779d8c1 Merge pull request #231 from ebolam/united henk717 2022-10-22 14:13:32 +02:00
  • f7b799be56 Apply tokenizer fixes to prompt_tuner.py vfbd 2022-10-21 17:06:17 -04:00
  • d588dc0096 Check if dir exists before creating ebolam 2022-10-19 11:19:04 -04:00
  • 73865ba066 Add parameter to Colab for not using google drive (data would be ephemeral) ebolam 2022-10-19 11:05:17 -04:00
  • f8be854e09 Merge branch 'KoboldAI:main' into united henk717 2022-10-17 21:06:10 +02:00
  • 2795ced3a4 Merge pull request #168 from VE-FORBRYDERNE/api-patch henk717 2022-10-17 20:38:34 +02:00
  • 9ff50d81fd Fix regex for the prompt parameter of the POST /story/end endpoint vfbd 2022-10-17 14:36:23 -04:00
  • c6ed656a76 Merge pull request #230 from pi6am/fix/lua_kobold_modeltype henk717 2022-10-14 19:50:19 +02:00
  • e5d0cc7b49 Fix exception thrown by kobold.modeltype in Lua Llama 2022-10-14 09:20:33 -07:00
  • 6eb3abbdb8 Merge pull request #2 from henk717/united Llama 2022-10-13 20:33:34 -07:00
  • fff7837a4a Merge pull request #229 from pi6am/feature/anote-kwarg henk717 2022-10-13 23:04:46 +02:00
  • be5ffe763c Merge pull request #228 from VE-FORBRYDERNE/transpose henk717 2022-10-13 15:35:28 +02:00
  • 8357c3e485 Merge branch 'united' into feature/anote-kwarg Llama 2022-10-12 23:37:45 -07:00
  • 05bcd3af11 Merge pull request #1 from henk717/united Llama 2022-10-12 23:32:25 -07:00
  • 4a01f345de Add include_anote kwarg to lua_compute_context. Llama 2022-10-12 23:18:19 -07:00
  • bdc73ef393 Decrease TPU loading times by eliminating a transpose operation vfbd 2022-10-12 14:31:18 -04:00
  • 59e3a40496 Merge pull request #165 from henk717/united 1.19.1 henk717 2022-10-12 15:35:09 +02:00
  • 64715b18d6 Version bump Henk 2022-10-12 14:54:11 +02:00
  • d5143eeb80 LUA Error as Error Henk 2022-10-12 01:23:00 +02:00
  • 739cf0aae7 Merge pull request #227 from VE-FORBRYDERNE/pickle henk717 2022-10-07 02:12:53 +02:00
  • 323f593a96 Custom unpickler to avoid pickle's arbitrary code execution vulnerability vfbd 2022-10-06 20:08:08 -04:00
  • b85d74f22c Merge branch 'KoboldAI:main' into united henk717 2022-10-05 19:51:29 +02:00
  • 9f18811ff9 Merge pull request #226 from VE-FORBRYDERNE/api-settings henk717 2022-10-04 20:30:25 +02:00
  • 6af0e842f2 Switch to official henk717 2022-10-04 17:42:18 +02:00
  • cf3aebbd8f Merge pull request #161 from henk717/united 1.19.0 henk717 2022-10-04 15:57:47 +02:00
  • bdfa6d86b7 Seed has to be a 64-bit unsigned int or PyTorch will throw an error tpu_mtj_backend's seed can be an integer of arbitrary size but we will limit it to a 64-bit unsigned integer anyways for consistency. vfbd 2022-10-02 17:50:32 -04:00
  • dd1c25241d Allow sampler seed and full determinism to be read/written in /config vfbd 2022-10-02 17:43:54 -04:00
  • 1a59a4acea Allow changing sampler seed and sampler order from API vfbd 2022-10-02 16:25:51 -04:00
  • 7bd3125f5a Merge branch 'KoboldAI:main' into united henk717 2022-10-01 16:59:46 +02:00
  • 2f45b93119 GPU updates henk717 2022-10-01 16:58:16 +02:00
  • e1606afc0d GPU Descriptions henk717 2022-10-01 15:43:45 +02:00
  • 8313df8817 Localtunnel Default henk717 2022-10-01 15:42:54 +02:00
  • 9abad8bee9 Merge pull request #225 from scythe000/united henk717 2022-09-30 19:30:46 +02:00
  • a482ec16d8 Update aiserver.py - typo fix scythe000 2022-09-30 10:29:32 -07:00
  • 276c6f8e9e Merge pull request #224 from db0/get_cluster_models_fix henk717 2022-09-30 00:30:18 +02:00
  • 90022d05c8 fix endpoint for get_cluster_models Divided by Zer0 2022-09-30 00:26:55 +02:00
  • 6758d5b538 Merge branch 'united' into mkultra vfbd 2022-09-28 14:30:34 -04:00
  • 3a094a049b Merge pull request #223 from ebolam/united henk717 2022-09-28 19:15:33 +02:00
  • e7973e13ac Fix for GPT models downloading even when present in model folder ebolam 2022-09-28 12:47:50 -04:00
  • 0f7ecb3257 Merge pull request #222 from ebolam/united henk717 2022-09-28 01:54:21 +02:00
  • f0690373b3 Merge branch 'united' of https://github.com/ebolam/KoboldAI into united ebolam 2022-09-27 19:52:44 -04:00
  • 72fc68c6e4 Fix for lazy loading on models after a non-lazy load model ebolam 2022-09-27 19:52:35 -04:00
  • c935d8646a Merge pull request #221 from ebolam/united henk717 2022-09-28 01:32:08 +02:00
  • 4aa842eada Merge commit 'refs/pull/180/head' of https://github.com/ebolam/KoboldAI into united ebolam 2022-09-27 19:29:05 -04:00
  • be719a7e5e Fix for loading models that don't support breakmodel (GPU/CPU support in UI) ebolam 2022-09-27 19:02:37 -04:00
  • 52e120c706 Disable breakmodel if we error on the check Henk 2022-09-28 01:00:06 +02:00
  • d2ff32be32 Merge pull request #220 from ebolam/united henk717 2022-09-28 00:46:37 +02:00
  • 057ddb4fb2 Better --cpu handling Henk 2022-09-28 00:45:17 +02:00
  • 168ae8083c Remove debug print ebolam 2022-09-27 18:30:20 -04:00
  • 0311cc215e Fix for loading models on CPU only that don't support breakmodel ebolam 2022-09-27 18:29:32 -04:00
  • 3906cc1bd0 Merge pull request #219 from ebolam/united henk717 2022-09-28 00:17:27 +02:00
  • edd50fc809 Fix for GPT2 breakmodel in the UI ebolam 2022-09-27 17:58:51 -04:00
  • f1d63f61f3 Syntax fix Henk 2022-09-27 22:43:09 +02:00
  • d772837ad0 Merge pull request #217 from ebolam/united henk717 2022-09-27 22:41:13 +02:00
  • 908dc8ea60 Fix for older model loading ebolam 2022-09-27 15:59:56 -04:00
  • 62921c4896 getmodelname for configname Henk 2022-09-27 21:11:31 +02:00
  • 6c32bc18d7 GPT2Tokenizer for TPU Henk 2022-09-27 18:33:31 +02:00
  • 60d09899ea Don't use Fast tokenizers when we don't have to Henk 2022-09-27 18:26:13 +02:00
  • 11455697ef Tokenizer Fixes (Slow first to keep coherency) Henk 2022-09-27 17:57:18 +02:00
  • 07896867b2 Revert Tokenizer Change Henk 2022-09-27 15:36:08 +02:00
  • 82a250aa1b Revert "Fix tokenizer selection code" 1.18.2 Henk 2022-09-27 15:33:08 +02:00
  • 7f5ba8a678 Merge pull request #216 from VE-FORBRYDERNE/merge henk717 2022-09-26 22:11:44 +02:00
  • 79ae0f17ec Merge branch 'main' into merge vfbd 2022-09-26 16:10:10 -04:00
  • 685ec3237b Merge pull request #158 from VE-FORBRYDERNE/tokenizer henk717 2022-09-26 21:34:26 +02:00
  • 39bd02a40e Merge pull request #157 from VE-FORBRYDERNE/patch henk717 2022-09-26 21:34:16 +02:00
  • 7fba1fd28a Fix tokenizer selection code vfbd 2022-09-26 14:37:25 -04:00
  • ddc9be00d6 Attempt to fix issue where | appears in editor after pressing enter vfbd 2022-09-26 13:57:44 -04:00
  • ce692c7ebf Pinned info toggle fix Henk 2022-09-26 16:36:50 +02:00
  • c88f88f54d Merge pull request #215 from ebolam/united henk717 2022-09-25 19:50:44 +02:00
  • 1f6861d55c Update for horde selection to pull models automatically (or on typing with a 1 second delay ebolam 2022-09-25 13:49:02 -04:00
  • 50266ab49a Torch fixes for colab Henk 2022-09-25 19:47:08 +02:00
  • b0a32d3646 Requirements Cleanup Henk 2022-09-25 19:40:59 +02:00
  • 9f15077337 Requirements Updates Henk 2022-09-25 19:33:18 +02:00
  • 6009586ac8 Requirements Updates Henk 2022-09-25 19:30:09 +02:00
  • 1a55088a21 Merge branch 'united' of https://github.com/henk717/koboldai into united Henk 2022-09-25 17:26:59 +02:00
  • d7ed577bf7 Don't stream in chatmode Henk 2022-09-25 17:26:52 +02:00
  • 0da5031955 Merge branch 'KoboldAI:main' into united henk717 2022-09-25 17:08:07 +02:00