Commit graph

  • 6235d43074
    Merge branch 'oobabooga:main' into main Shixian Sheng 2024-06-15 09:11:43 -0400
  • 1f5f1612e3 Make logs more readable, no more \u7f16\u7801 Touch-Night 2024-06-15 15:34:05 +0800
  • b6eaf7923e Bump llama-cpp-python to 0.2.78 oobabooga 2024-06-14 21:22:09 -0700
  • 76c76584f3 Typing Artificiangel 2024-06-14 20:52:02 -0400
  • 9420973b62
    Downgrade PyTorch to 2.2.2 (#6124) oobabooga 2024-06-14 16:42:03 -0300
  • c9d17603ff Update some wheels oobabooga 2024-06-14 12:40:32 -0700
  • 1576227f16
    Fix GGUFs with no BOS token present, mainly qwen2 models. (#6119) Forkoz 2024-06-14 11:51:01 -0500
  • 0b39b5c73f Set bos_token = "" oobabooga 2024-06-14 09:50:20 -0700
  • 2123a2bda9 Downgrate PyTorch to 2.2.2 oobabooga 2024-06-14 09:49:00 -0700
  • fdd8fab9cf
    Bump hqq from 0.1.7.post2 to 0.1.7.post3 (#6090) dependabot[bot] 2024-06-14 13:46:35 -0300
  • 10601850d9 Fix after previous commit oobabooga 2024-06-13 19:54:12 -0700
  • 0f3a423de1 Alternative solution to "get next logits" deadlock (#6106) oobabooga 2024-06-13 19:33:15 -0700
  • 9aef01551d Revert "Use reentrant generation lock (#6107)" oobabooga 2024-06-13 17:53:07 -0700
  • 8930bfc5f4
    Bump PyTorch, ExLlamaV2, flash-attention (#6122) oobabooga 2024-06-13 20:38:31 -0300
  • fb3eb11cb6 Bump flash-attention (Windows) oobabooga 2024-06-13 16:21:57 -0700
  • 3f1e7a9847 Bump flash-attention (Linux) oobabooga 2024-06-13 09:13:20 -0700
  • 34e45bff73
    Update models_settings.py Forkoz 2024-06-13 08:47:06 -0500
  • 87dc23530c Bump ExLlamaV2 to 0.1.5 oobabooga 2024-06-13 06:17:24 -0700
  • bdfd608028 Bump PyTorch to 2.3.1 oobabooga 2024-06-13 05:54:02 -0700
  • 386500aa37 Avoid unnecessary calls UI -> backend, to make it faster oobabooga 2024-06-12 20:52:42 -0700
  • 0afed24269
    Bump hqq from 0.1.5 to 0.1.7.post3 dependabot[bot] 2024-06-13 03:39:12 +0000
  • 3db5528aab
    Update gradio requirement from ==4.26.* to ==4.36.* dependabot[bot] 2024-06-13 03:39:12 +0000
  • 4820ae9aef
    Merge pull request #6118 from oobabooga/dev oobabooga 2024-06-13 00:38:03 -0300
  • 1d79aa67cf
    Fix flash-attn UI parameter to actually store true. (#6076) Forkoz 2024-06-13 03:34:54 +0000
  • 08a310a778 Undo unnecessary changes oobabooga 2024-06-12 20:30:08 -0700
  • 3abafee696
    DRY sampler improvements (#6053) Belladore 2024-06-13 05:39:11 +0300
  • b556ee2800 lint oobabooga 2024-06-12 19:37:49 -0700
  • ed43c5e494 Merge branch 'dev' into belladoreai-dev-dry-optimization2 oobabooga 2024-06-12 19:36:49 -0700
  • b675151f25
    Use reentrant generation lock (#6107) theo77186 2024-06-13 04:25:05 +0200
  • a36fa73071 Lint oobabooga 2024-06-12 19:00:21 -0700
  • 2d196ed2fe Remove obsolete pre_layer parameter oobabooga 2024-06-12 18:56:44 -0700
  • 46174a2d33
    Fix error when bos_token_id is None. (#6061) Belladore 2024-06-13 04:52:27 +0300
  • 98443196d1
    Merge branch 'oobabooga:dev' into dev Artificiangel 2024-06-12 21:05:35 -0400
  • 0270af4101 Revert "Use custom model/lora download folder in model downloader" Artificiangel 2024-06-12 21:04:48 -0400
  • 603375bfc5
    Update models_settings.py: add default alpha_value, add proper compress_pos_emb for newer GGUFs mefich 2024-06-09 23:58:00 +0500
  • f8ab5bcdac
    Update docker-image.yml xerhab 2024-06-08 15:07:32 -0400
  • 7b7a29648d
    Merge pull request #8 from xerktech/syncrate xerhab 2024-06-07 15:43:46 -0400
  • 570fc68160
    Update syncfork.yaml xerhab 2024-06-07 15:43:35 -0400
  • a4802381f1
    Merge pull request #7 from xerktech/workflows4 xerhab 2024-06-07 15:30:20 -0400
  • 9092c40320
    Update docker-image.yml xerhab 2024-06-07 15:30:02 -0400
  • 554c0d2ffb
    Merge pull request #6 from xerktech/workflow3 xerhab 2024-06-07 15:01:56 -0400
  • 24ad2ce8da
    Update docker-image.yml xerhab 2024-06-07 15:01:45 -0400
  • 63a8d6a789
    Merge pull request #5 from xerktech/workflow2 xerhab 2024-06-07 14:59:39 -0400
  • e6b2cfc8d6
    Update docker-image.yml xerhab 2024-06-07 14:59:16 -0400
  • 82f58c3172
    Merge pull request #4 from xerktech/workflows xerhab 2024-06-07 14:56:19 -0400
  • 1d2cad2483
    Update docker-image.yml xerhab 2024-06-07 14:54:55 -0400
  • b4631a7fb8
    Delete .github/pull_request_template.md xerhab 2024-06-07 14:54:19 -0400
  • ad55eb867c
    Merge pull request #3 from xerktech/docker2-2 xerhab 2024-06-07 14:49:12 -0400
  • 88a3421e43
    Update docker-image.yml xerhab 2024-06-07 14:48:39 -0400
  • ca96bcb5b1
    Merge pull request #2 from xerktech/Docker-Workflow xerhab 2024-06-07 14:18:07 -0400
  • c85f59c95f
    Create docker-image.yml xerhab 2024-06-07 14:17:53 -0400
  • 77d769ef6e
    Merge pull request #1 from xerktech/xerhab-patch-1 xerhab 2024-06-07 14:00:31 -0400
  • 88319ff0e9
    Update syncfork.yaml xerhab 2024-06-07 13:59:58 -0400
  • fe3a90141f
    Create syncfork.yaml xerhab 2024-06-07 13:52:06 -0400
  • 9cdc84df4b
    Use reentrant generation lock theo77186 2024-06-07 16:55:17 +0200
  • 00eed08b5e
    Update README.md Forkoz 2024-06-04 17:01:16 +0000
  • 8178540ffe
    Update ui_model_menu.py Guanghua Lu 2024-06-04 11:48:09 +0800
  • 9fee8ccde1
    Update ui.py Guanghua Lu 2024-06-04 11:47:18 +0800
  • ae7414ae46
    Update loaders.py Guanghua Lu 2024-06-04 11:46:10 +0800
  • 8517ee7342
    Update gradio requirement from ==4.26.* to ==4.32.* dependabot[bot] 2024-06-03 20:32:55 +0000
  • 785f53ab07
    Update optimum requirement from ==1.17.* to ==1.20.* dependabot[bot] 2024-06-03 20:32:40 +0000
  • 9372fb3cf9 Send your images to llamacpp_hf, wrong and slow Touch-Night 2024-06-03 21:12:44 +0800
  • 9a33e4f457 Accelerate DRYLogitsProcessor by using numpy on cpu (fix #5677) Jonas Tingeborn 2024-06-03 06:49:36 +0200
  • abaca1e0a9
    Update extensions/openai/completions.py Koesn 2024-06-02 20:22:36 +0700
  • 605487ab32
    Add files via upload Guanghua Lu 2024-06-02 19:20:35 +0800
  • d8caa3ca56 Multimodal support for llamacpp_hf, not working embed_tokens() is not working, need to fix it Touch-Night 2024-06-02 19:13:06 +0800
  • 2ac2ed9d5d improve GGUF metadata handling ddh0 2024-06-01 22:39:04 -0500
  • 98c6065615
    Merge pull request #4 from blackmambaza/modules-html-gen-improvements blackmambaza 2024-06-02 00:44:22 +0200
  • 4696b1a362
    Improved consistency of HTML generator blackmambaza 2024-06-02 00:43:50 +0200
  • 66697d913c
    Merge pull request #3 from blackmambaza/modules-ui-chat-performance-improvements blackmambaza 2024-06-02 00:35:30 +0200
  • b770d142da
    Improved performance and state management on the chat ui blackmambaza 2024-06-02 00:33:54 +0200
  • fb5a9387c6
    Merge pull request #2 from blackmambaza/revert-1-modules-chat-improvements blackmambaza 2024-06-01 23:34:20 +0200
  • e55d57a01f
    Revert "Reduces cognitive complexity of chat module and improves string opera…" blackmambaza 2024-06-01 23:33:40 +0200
  • 71111d2854
    Merge pull request #1 from blackmambaza/modules-chat-improvements blackmambaza 2024-06-01 23:32:40 +0200
  • d133ef1443
    Reduces cognitive complexity of chat module and improves string operations blackmambaza 2024-06-01 23:30:07 +0200
  • bd2a18e089
    Fix ui_model_menu.py Forkoz 2024-06-01 12:28:20 +0000
  • 776f320d28
    Fix loaders.py Forkoz 2024-06-01 12:27:30 +0000
  • ca6765bbe1
    Fix ui.py Forkoz 2024-06-01 12:26:56 +0000
  • 03c1a9bae1
    Fix shared.py Forkoz 2024-06-01 12:25:55 +0000
  • 7ce96dc25f A small fix Touch-Night 2024-06-01 11:24:41 +0800
  • 248d9cc647 Also, you can use llamacpp_hf to load multimodal model, however it's not working now, you can only load it but can't use it to do anything. Touch-Night 2024-05-31 01:03:51 +0800
  • 9b1da75ebd Now you can load multimodal models in llama.cpp Touch-Night 2024-05-31 00:40:00 +0800
  • 904c53dec7 Add pipelines folder to .gitignore Touch-Night 2024-05-30 01:09:57 +0800
  • e8d714d514 Remove instructblip-pipeline from the repo. Touch-Night 2024-05-30 01:07:44 +0800
  • fcdd9d06f1 Intergrated multimodal functionality Touch-Night 2024-05-30 01:03:54 +0800
  • 0957563429
    Merge fbf4d6996e into a363cdfca1 Eve 2024-05-28 21:21:36 +0300
  • 686e7a8344 Comment. Belladore 2024-05-28 12:39:04 +0300
  • 1e9cf3d284 Fix error when bos_token_id is None. Belladore 2024-05-28 12:30:42 +0300
  • 47c774e8a3 Add proper warning message for decode failure nclok1405 2024-05-28 00:54:54 +0900
  • f5ca611569 Fallback to latin on decode failure nclok1405 2024-05-28 00:45:06 +0900
  • a363cdfca1
    Fix missing bos token for some models (including Llama-3) (#6050) Belladore 2024-05-27 15:21:30 +0300
  • c5064d074c Minor changes/checks oobabooga 2024-05-27 05:17:56 -0700
  • 8df68b05e9 Remove MinPLogitsWarper (it's now a transformers built-in) oobabooga 2024-05-27 05:03:30 -0700
  • 918ff94f1d Change DRY max match length. Belladore 2024-05-26 23:22:55 +0300
  • 62e76edcab Rename variable. Belladore 2024-05-26 23:14:14 +0300
  • 3c51b955e1 Fix DRY crash on very repetitive inputs. Belladore 2024-05-25 18:19:19 +0300
  • 1005c3d219 Refactor DRY sampler. Belladore 2024-05-24 20:52:11 +0300
  • c059d9b650 Minor fix to prevent DRY sampler crash on very long repetitive inputs. Belladore 2024-05-24 17:58:33 +0300
  • 4f1e96b9e3 Downloader: Add --model-dir argument, respect --model-dir in the UI oobabooga 2024-05-23 20:42:46 -0700
  • d78159ccb3 Fix missing bos token (affecting many llama 3 exl2 quants and probably other models too). Belladore 2024-05-24 01:59:19 +0300