Commit Graph

  • f0538efb99 Remove obsolete --tensorcores references oobabooga 2024-04-24 00:31:28 -0700
  • f3c9103e04
    Revert walrus operator for params['max_memory'] (#5878) Colin 2024-04-24 00:09:14 -0400
  • c725d97368
    nvidia docker: make sure gradio listens on 0.0.0.0 (#5918) Jari Van Melckebeke 2024-04-24 04:17:55 +0200
  • 9b623b8a78
    Bump llama-cpp-python to 0.2.64, use official wheels (#5921) oobabooga 2024-04-23 23:17:05 -0300
  • c7c1a39992 Update README oobabooga 2024-04-23 19:16:06 -0700
  • b0d23bf46d Handle the cuda118 case oobabooga 2024-04-23 19:12:04 -0700
  • 2666a59b0e Bump llama-cpp-python to 0.2.64, use official wheels oobabooga 2024-04-23 18:51:36 -0700
  • 905706a827
    Update Dockerfile Jari Van Melckebeke 2024-04-23 13:49:39 +0200
  • a1211f7620
    update path for docker-compose.yaml in code example Jari Van Melckebeke 2024-04-23 13:31:46 +0200
  • 5d2e8f958b
    Update README.md Jari Van Melckebeke 2024-04-23 13:29:57 +0200
  • ba5001b3b1 Restore conditional assign of max_memory value Column01 2024-04-22 13:50:55 -0400
  • 5007367235
    Merge pull request #1 from Column01/fix-model-params Colin 2024-04-22 13:47:06 -0400
  • 200e0dc197 Replace direct key access with .get methods Column01 2024-04-22 13:46:05 -0400
  • 4a388da98e
    Merge branch 'oobabooga:main' into main Colin 2024-04-22 13:40:19 -0400
  • fbf4d6996e
    fix handling of prefix with intentional space Eve 2024-04-22 04:26:06 +0000
  • af81277044
    Merge 857a2ca5b3 into 0877741b03 Eve 2024-04-22 04:18:09 +0000
  • 857a2ca5b3 Merge remote-tracking branch 'origin/dev' into fix_trailing_spaces netrunnereve 2024-04-22 00:16:14 -0400
  • 81ea2783af update API documentation with examples to list/load models Joachim Chauveheid 2024-04-21 20:13:58 +0300
  • 55306aa4e1 feat: save chat template with instruction template A0nameless0man 2024-04-21 16:10:59 +0000
  • c93c867397 fix: grammar not support utf-8 A0nameless0man 2024-04-21 16:07:12 +0000
  • e5d608ed60
    Update ChatML-format.json FartyPants (FP HAM) 2024-04-21 10:43:46 -0400
  • 7d40cb70cb
    Added ChatML-format.json in formats, since people are still puzzled FartyPants (FP HAM) 2024-04-21 10:41:14 -0400
  • b09badffea
    Merge 47a8d8b520 into 0877741b03 Stefan Daniel Schwarz 2024-04-21 10:26:19 -0400
  • baa4dde9b3 Remove BOS token in the template Touch-Night 2024-04-21 01:54:10 +0800
  • 8ad0222547 Correct Llama-v3 template Touch-Night 2024-04-21 01:12:33 +0800
  • b460d0d35b Add Llama 3 template Touch-Night 2024-04-20 20:11:50 +0800
  • 0877741b03
    Bumped ExLlamaV2 to version 0.0.19 to resolve #5851 (#5880) Ashley Kleynhans 2024-04-20 00:04:40 +0200
  • f1e8f66a9a
    Bumped ExLlamaV2 to version 0.0.19 in the other requirements files to resolve #5851 Ashley Kleynhans 2024-04-19 17:40:36 +0200
  • a4b732c30b
    Merge pull request #5887 from oobabooga/dev snapshot-2024-04-21 oobabooga 2024-04-19 12:34:50 -0300
  • 4a4c142f36
    Bumped ExLlamaV2 to version 0.0.19 to resolve #5851 Ashley Kleynhans 2024-04-19 09:50:34 +0200
  • f27e1ba302
    Add a /v1/internal/chat-prompt endpoint (#5879) oobabooga 2024-04-19 00:24:46 -0300
  • 806e9fd525 Add the loader to the /internal/model/info endpoint oobabooga 2024-04-18 20:18:10 -0700
  • 8a16ad00ef
    Revert walrus operator for params['max_memory'] Colin 2024-04-18 21:54:53 -0400
  • 63dbfcbfd9 Fix the "continue" option oobabooga 2024-04-18 16:40:10 -0700
  • d91ef0e10a Add a /v1/internal/chat-prompt endpoint oobabooga 2024-04-18 16:18:04 -0700
  • b30bce3b2f Bump transformers to 4.40 oobabooga 2024-04-18 15:55:34 -0700
  • a0c69749e6
    Revert sse-starlette version bump because it breaks API request cancellation (#5873) Philipp Emanuel Weidmann 2024-04-18 23:35:00 +0530
  • d8fd931524
    Revert "Bump sse-starlette from 1.6.5 to 2.1.0 (#5831)" Philipp Emanuel Weidmann 2024-04-18 14:34:29 +0530
  • c42afd5b42 Let grammar escape backslashes altoiddealer 2024-04-15 21:00:36 -0400
  • b90fd35998
    fix cloudflare request blocker str/byte mismatch Googolplexed0 2024-04-15 18:58:43 -0400
  • dc50307622
    Update optimum requirement from ==1.17.* to ==1.18.* dependabot[bot] 2024-04-15 20:19:15 +0000
  • ac5e2d087a sort multipart gguf files by name Tisjwlf 2024-04-14 17:56:18 +0200
  • 8985a8538b
    Fix whisper STT (#5856) mamei16 2024-04-14 15:55:58 +0200
  • 9d60c6c65b use stop_recording audio event listener instead of change marcel 2024-04-14 04:10:02 +0200
  • 41aa53ccf2
    fix handling of prefix with intentional space Eve 2024-04-13 04:00:24 +0000
  • 26d822f64f
    Merge pull request #5848 from oobabooga/dev snapshot-2024-04-14 oobabooga 2024-04-12 12:46:25 -0300
  • 597556cb77
    Bump sse-starlette from 1.6.5 to 2.1.0 (#5831) dependabot[bot] 2024-04-11 18:54:05 -0300
  • e158299fb4 Fix loading sharted GGUF models through llamacpp_HF oobabooga 2024-04-11 14:50:05 -0700
  • fd4e46bce2
    Add Ascend NPU support (basic) (#5541) wangshuai09 2024-04-12 05:42:20 +0800
  • 5348558d4d Clean up oobabooga 2024-04-11 14:39:09 -0700
  • 8ec2d65203 Lint oobabooga 2024-04-11 14:36:07 -0700
  • e4abede667 Remove from one-click installer oobabooga 2024-04-11 14:34:55 -0700
  • eb06e7e572 Merge branch 'dev' into wangshuai09-npu_support oobabooga 2024-04-11 14:34:17 -0700
  • a90509d82e
    Model downloader: Take HF_ENDPOINT in consideration (#5571) zaypen 2024-04-12 05:28:10 +0800
  • 70c637bf90
    Fix saving of UI defaults to settings.yaml - Fixes #5592 (#5794) Ashley Kleynhans 2024-04-11 23:19:16 +0200
  • 3e3a7c4250 Bump llama-cpp-python to 0.2.61 & fix the crash oobabooga 2024-04-11 14:15:34 -0700
  • 5f5ceaf025 Revert "Bump llama-cpp-python to 0.2.61" oobabooga 2024-04-11 13:24:57 -0700
  • bd71a504b8
    Update gradio requirement from ==4.25.* to ==4.26.* (#5832) dependabot[bot] 2024-04-11 02:24:53 -0300
  • c423d51a83
    Fix issue #5783 for character images with transparency (#5827) Victorivus 2024-04-11 07:23:43 +0200
  • 98da23fce2 Fix a bug oobabooga 2024-04-10 22:14:56 -0700
  • bc7a54b445 Organize oobabooga 2024-04-10 22:13:50 -0700
  • a7f9754b2a Remove dry_range, make DRY a LogitsProcessor oobabooga 2024-04-10 22:09:40 -0700
  • f3f955cc4c Reorganize the UI oobabooga 2024-04-10 22:09:22 -0700
  • 09b9da5669 Merge branch 'dev' into p-e-w-dry oobabooga 2024-04-10 21:56:26 -0700
  • b94cd6754e
    UI: Respect model and lora directory settings when downloading files (#5842) Alex O'Connell 2024-04-11 04:55:02 +0000
  • 17c4319e2d Fix loading command-r context length metadata oobabooga 2024-04-10 21:36:32 -0700
  • 3ae61c0338 Bump llama-cpp-python to 0.2.61 oobabooga 2024-04-10 21:36:06 -0700
  • fb32baebb7
    Respect model and lora directory settings when downloading files Alex O'Connell 2024-04-10 23:15:13 +0000
  • cbd65ba767
    Add a simple min_p preset, make it the default (#5836) oobabooga 2024-04-09 12:50:16 -0300
  • dd8ddc0720
    Update README.md sumit9923o8u 2024-04-09 19:02:27 +0530
  • 6bf88e3576
    Update README.md sumit9923o8u 2024-04-09 17:20:43 +0530
  • de0f6bfd9e Add a simple min_p preset, make it the default oobabooga 2024-04-08 18:16:58 -0700
  • ed4001e324 Bump ExLlamaV2 to 0.0.18 oobabooga 2024-04-08 18:05:16 -0700
  • 33665b3343
    Update gradio requirement from ==4.25.* to ==4.26.* dependabot[bot] 2024-04-08 20:43:06 +0000
  • d423617413
    Bump sse-starlette from 1.6.5 to 2.1.0 dependabot[bot] 2024-04-08 20:42:57 +0000
  • 327a824cd4
    Bump hqq from 0.1.5 to 0.1.6.post2 dependabot[bot] 2024-04-08 20:42:53 +0000
  • 7db49f341c
    Bump lm-eval from 0.3.0 to 0.4.2 dependabot[bot] 2024-04-08 20:42:51 +0000
  • 2711fe46af
    Bump aqlm[cpu,gpu] from 1.1.3 to 1.1.4 dependabot[bot] 2024-04-08 20:42:46 +0000
  • 1d55c9c143
    FIX Issue #5783 Transparency to image cache Victorivus 2024-04-08 17:56:45 +0200
  • 91a7370a65
    Merge pull request #5823 from oobabooga/dev snapshot-2024-04-07 oobabooga 2024-04-07 11:01:08 -0300
  • f6828de3f2 Downgrade llama-cpp-python to 0.2.56 oobabooga 2024-04-07 07:00:12 -0700
  • 39ff9c9dcf
    requirements: add psutil (#5819) Jared Van Bortel 2024-04-06 22:02:20 -0400
  • 65099dc192
    Merge pull request #5822 from oobabooga/dev oobabooga 2024-04-06 22:58:06 -0300
  • d02744282b Minor logging change oobabooga 2024-04-06 18:56:58 -0700
  • dfb01f9a63 Bump llama-cpp-python to 0.2.60 oobabooga 2024-04-06 18:32:36 -0700
  • 9c51fb1fc5 requirements: add psutil Jared Van Bortel 2024-04-06 20:06:49 -0400
  • 096f75a432 Documentation: remove obsolete RWKV docs oobabooga 2024-04-06 14:06:39 -0700
  • dd6e4ac55f Prevent double <BOS_TOKEN> with Command R+ oobabooga 2024-04-06 13:12:16 -0700
  • 1bdceea2d4 UI: Focus on the chat input after starting a new chat oobabooga 2024-04-06 12:57:57 -0700
  • 168a0f4f67 UI: do not load the "gallery" extension by default oobabooga 2024-04-06 12:43:21 -0700
  • 64a76856bd Metadata: Fix loading Command R+ template with multiple options oobabooga 2024-04-06 07:32:17 -0700
  • 1b87844928 Minor fix oobabooga 2024-04-05 18:43:43 -0700
  • 6b7f7555fc Logging message to make transformers loader a bit more transparent oobabooga 2024-04-05 18:40:02 -0700
  • 4e739dc211 Add an instruction template for Command R oobabooga 2024-04-05 18:22:25 -0700
  • 8a8dbf2f16 Merge remote-tracking branch 'refs/remotes/origin/dev' into dev oobabooga 2024-04-05 12:42:23 -0700
  • 0f536dd97d UI: Fix the "Show controls" action oobabooga 2024-04-05 12:17:54 -0700
  • a4c67e1974
    Bump aqlm[cpu,gpu] from 1.1.2 to 1.1.3 (#5790) dependabot[bot] 2024-04-05 13:26:49 -0300
  • 14f6194211 Bump Gradio to 4.25 oobabooga 2024-04-05 09:22:44 -0700
  • 5b91dbb73b
    Merge pull request #5810 from oobabooga/dev oobabooga 2024-04-05 10:55:16 -0300
  • 308452b783 Bitsandbytes: load preconverted 4bit models without additional flags oobabooga 2024-04-04 18:09:34 -0700