Commit Graph

  • b14c5443fd API: Add sampler override switching kingbri 2024-01-24 01:20:58 -05:00
  • de0ba7214c API: Add template switching and unload endpoints kingbri 2024-01-22 23:13:52 -05:00
  • 6c30f24c83 Tree: Unify sampler parameters and add override support kingbri 2024-01-21 23:34:44 -05:00
  • 78f920eeda Tree: Refactor code organization kingbri 2024-01-18 00:42:52 -05:00
  • ee99349a78 Requirements: Bump exllamav2 kingbri 2024-01-22 21:13:31 -05:00
  • 902e841c39 Main: Add logging for API routes kingbri 2024-01-10 23:50:11 -05:00
  • 7a29664f06 API: Add alias names to field descriptions kingbri 2024-01-08 23:00:33 -05:00
  • 1dbebd48eb Merge pull request #50 from djmaze/patch-1 Brian Dashore 2024-01-06 00:10:20 -05:00
  • 6ab02e1eeb Remove fschat from compose yaml Martin Honermeyer 2024-01-06 02:18:26 +01:00
  • 81b504e8c5 OAI: Fix typical alias kingbri 2024-01-05 16:38:39 -05:00
  • 2c57dafc59 OAI: Add alias for typical sampling kingbri 2024-01-05 15:29:53 -05:00
  • d4ed9f703d Tree: Format kingbri 2024-01-04 21:13:30 -05:00
  • c1642076c2 API: Switch unload method to POST kingbri 2024-01-04 21:11:36 -05:00
  • cd4bf99598 OAI: Fix autodoc examples for model loading kingbri 2024-01-04 20:53:56 -05:00
  • ceb388e8a0 Start: Override ROCm env variables kingbri 2024-01-02 21:00:22 -05:00
  • c980f35e1b Merge pull request #47 from Baysul/patch-1 Brian Dashore 2024-01-02 20:58:59 -05:00
  • 2460b2f8ef Only try to install one of the EXLv2 wheels Basil 2024-01-02 16:56:39 -08:00
  • 451042aadf Main: Don't load if model_name/loras is blank kingbri 2024-01-02 13:56:25 -05:00
  • 6b04463051 API: Fix CFG reporting kingbri 2024-01-02 13:54:16 -05:00
  • bbd4ee54ca Model: Add fallback if negative prompt is empty kingbri 2024-01-02 01:38:03 -05:00
  • b378773d0a Model: Add CFG support kingbri 2024-01-02 01:09:26 -05:00
  • bb7a8e4614 Config: Add override argparser kingbri 2024-01-01 14:27:12 -05:00
  • 7176fa66f0 Update README kingbri 2023-12-31 11:25:18 -05:00
  • 979a9d28a3 Tree: Format kingbri 2023-12-31 11:22:18 -05:00
  • 528d20ca5b Update README kingbri 2023-12-31 11:21:13 -05:00
  • 72bc30343c Model: Fix frequency penalty fallback kingbri 2023-12-31 11:12:14 -05:00
  • 47744fe9f7 Update README kingbri 2023-12-31 01:48:10 -05:00
  • 0dc12d82d5 Model: Add fallback for freq and presence pen kingbri 2023-12-30 00:24:15 -05:00
  • 79a57588d5 API: Add template list endpoint kingbri 2023-12-29 22:56:47 -05:00
  • dce8c74edc API: Add clarification and cleanup autodocs kingbri 2023-12-29 10:28:06 -05:00
  • 4136f19058 Config: Make the sample a drop-in solution kingbri 2023-12-29 01:36:21 -05:00
  • ec929728d9 Model: Read scale_pos_emb from config kingbri 2023-12-28 21:14:24 -05:00
  • e70729b0c0 Update Docker city-unit 2023-12-27 23:39:33 -05:00
  • 5dc2df68be Model: Repetition penalty range -> penalty range kingbri 2023-12-28 18:10:19 -05:00
  • c72d30918c Config: Default None -> Empty in comments kingbri 2023-12-28 00:32:29 -05:00
  • f56221ff0c Tree: Format kingbri 2023-12-28 00:31:59 -05:00
  • 3622710582 API: Fix num_experts_per_token reporting kingbri 2023-12-28 00:31:14 -05:00
  • c5bbfd97b2 Entrypoint: Load loras after model kingbri 2023-12-27 23:55:02 -05:00
  • ee84d892b8 Start: Add shell script kingbri 2023-12-27 23:53:14 -05:00
  • ac0d6f8869 Tree: Format and cleanup start kingbri 2023-12-27 01:13:13 -05:00
  • 4d83d1aae4 Start: Switch to python script kingbri 2023-12-27 00:37:53 -05:00
  • a71b96a20c Main: Switch to entrypoint kingbri 2023-12-26 22:57:45 -05:00
  • e92ef8f5c7 OAI: Fix rep pen range alias kingbri 2023-12-25 15:33:26 -05:00
  • 7b74cb28e6 Model: Move unsupported sampler check kingbri 2023-12-25 15:29:51 -05:00
  • e256ff8182 Samplers: Add frequency and presence penalty kingbri 2023-12-25 15:17:04 -05:00
  • 442bb59f8f Tests: Remove logger class kingbri 2023-12-25 14:40:40 -05:00
  • 162c13752a Requirements: Update to Flash Attention 2.4.1 kingbri 2023-12-25 14:40:08 -05:00
  • 5c08316d18 Start: Switch to Write-Host kingbri 2023-12-25 11:59:58 -05:00
  • 670ccac19a Start: Add option to not install wheels kingbri 2023-12-25 11:49:56 -05:00
  • 09ae71aa91 OAI: Add finish to completions kingbri 2023-12-25 11:25:38 -05:00
  • cc3229c109 Scripts: Make Start.bat idiotproof kingbri 2023-12-24 20:50:24 -05:00
  • 060d422e03 Config: Resolve filepath kingbri 2023-12-23 23:57:33 -05:00
  • 703a114f63 Tree: Format kingbri 2023-12-23 23:03:28 -05:00
  • c9126c3145 Config: Isolate to a separate file kingbri 2023-12-23 23:02:37 -05:00
  • 0d2e726e82 Main: Fix import formatting kingbri 2023-12-23 21:33:15 -05:00
  • 3461f8294f Logging: Clarify preferences kingbri 2023-12-23 20:58:50 -05:00
  • 98a7b951b9 Logging: Add newlines to Prompt and Response kingbri 2023-12-22 23:55:22 -05:00
  • 80ef379721 Sampling: Add top-a support kingbri 2023-12-22 23:50:24 -05:00
  • 6a5bbd217c feat: logging (#39) AlpinDale 2023-12-23 04:33:31 +00:00
  • f5314fcdad Merge pull request #37 from DocShotgun/main Brian Dashore 2023-12-22 12:07:52 -05:00
  • 71f6a586f1 Templates: Add error handling for template errors kingbri 2023-12-22 11:59:47 -05:00
  • fa47f51f85 feat: workflows for formatting/linting (#35) AlpinDale 2023-12-22 16:20:35 +00:00
  • a14abfe21c Templates: Support bos_token and eos_token fields kingbri 2023-12-22 10:31:50 -05:00
  • 7967607f12 Colab: Expose new config arguments DocShotgun 2023-12-22 01:53:13 -08:00
  • 2bf8087de3 Merge pull request #36 from veden/dev Brian Dashore 2023-12-22 00:34:19 -05:00
  • 91e6823b24 fixed method invocation in get_template_from_model_json Veden 2023-12-21 21:25:59 -08:00
  • 8fa764bfbe Auth: Add option to disable authentication kingbri 2023-12-21 23:40:16 -05:00
  • 99a798e117 API: Add auth enforcement to draft list kingbri 2023-12-21 23:14:04 -05:00
  • 5d80a049ae Templates: Switch to common function for JSON loading kingbri 2023-12-21 23:08:51 -05:00
  • 72e19dbc12 Config: Change default dirs in sample kingbri 2023-12-21 22:28:48 -05:00
  • 87a9dfc8c4 Merge pull request #34 from veden/dev Brian Dashore 2023-12-21 22:34:53 -05:00
  • 1a8afcb6ad Generator: Fix semaphore scheduling kingbri 2023-12-21 21:39:45 -05:00
  • f53c98db94 Templates: Added automatic detection of chat templates from tokenizer_config.json Aaron Veden 2023-12-20 22:45:55 -08:00
  • bee758dae9 Config: Clarify rope parameters kingbri 2023-12-20 21:15:06 -05:00
  • 5728b9fffb Model: Don't error out if a generation is empty kingbri 2023-12-20 00:51:33 -05:00
  • ab10b263fd Model: Add override base seq len kingbri 2023-12-20 00:43:19 -05:00
  • 5368ed7b64 Merge pull request #31 from veryamazinglystupid/main Brian Dashore 2023-12-20 00:04:51 -05:00
  • 5fbb37405f Colab: Remove the pydantic hotfix kingbri 2023-12-20 00:01:58 -05:00
  • c9e43e51aa API: Add route for draft model list kingbri 2023-12-19 23:45:53 -05:00
  • ce2602df9a Model: Fix max seq len handling kingbri 2023-12-19 23:37:52 -05:00
  • d3246747c0 Templates: Attempt loading from model config kingbri 2023-12-19 22:58:47 -05:00
  • da69ad8cd3 Requirements: Pin versions for some dependencies kingbri 2023-12-19 21:48:04 -05:00
  • 1fd38c61de API: Remove model check dependency for lora list kingbri 2023-12-19 21:35:29 -05:00
  • 12bf7a0174 fix the colab, pydantic error veryamazinglystupid 2023-12-19 19:46:57 +05:30
  • 0a144688c6 Templates: Add clarity statements kingbri 2023-12-19 08:13:04 -05:00
  • 0d76ed9b8b Revert "Start: Add an argument parser to batch file" kingbri 2023-12-19 00:01:27 -05:00
  • 45e2987622 Start: Fix batch file condition kingbri 2023-12-18 23:57:30 -05:00
  • 097c298c39 Start: Add an argument parser to batch file kingbri 2023-12-18 23:19:58 -05:00
  • c3f7898967 OAI: Add logit bias support kingbri 2023-12-18 18:04:12 -05:00
  • 46f6dc824e Scripts: Add requirements update to start script kingbri 2023-12-18 00:46:15 -05:00
  • 1f2cc8a47b Templates: Update folder kingbri 2023-12-17 23:22:58 -05:00
  • bc21f0bbc0 OAI: Add field aliasing kingbri 2023-12-17 21:57:46 -05:00
  • 124e39df26 Remove fschat from Dockerfile kingbri 2023-12-17 21:45:23 -05:00
  • de9a19b5d3 Templating: Add generation prompt appending kingbri 2023-12-17 21:34:31 -05:00
  • 041070fd6e Update gitignore kingbri 2023-12-17 20:17:13 -05:00
  • 417cb958fa Auth: Only regenerate auth on OSError kingbri 2023-12-17 17:33:51 -05:00
  • a87e474660 OAI: Fix chat completion validation kingbri 2023-12-17 16:00:22 -05:00
  • 7cbc08fc72 Templates: Add auto-detection from path kingbri 2023-12-17 15:41:09 -05:00
  • e895eaa4bd OAI: Clarify types in docs kingbri 2023-12-17 14:20:56 -05:00
  • 51ca1ff396 Tree: Switch to Pydantic 2 kingbri 2023-12-17 01:06:10 -05:00