Commit graph

  • 0af6a38af3 Model: Add logprobs support kingbri 2024-02-07 21:41:15 -05:00
  • 2642ef7156 OAI: Update logprobs type kingbri 2024-02-03 01:06:43 -05:00
  • 284f20263f API: Clean up tokenizing endpoint kingbri 2024-02-05 00:20:10 -05:00
  • bb48f77ca1
    Neutralize samplers (#59) AliCat 2024-02-07 22:23:09 -07:00
  • 321c9a1ea9 Requirements: Fix FA2 version number kingbri 2024-02-07 21:37:30 -05:00
  • 58590a6c57 Config: Add option to force streaming off kingbri 2024-02-07 21:08:21 -05:00
  • d0027bce32 Requirements: Update flash attention 2 for Windows kingbri 2024-02-07 20:44:23 -05:00
  • c0ad647fa7 Model: Auto-detect a one GPU setup and fix gpu_split_auto kingbri 2024-02-06 22:58:55 -05:00
  • 849179df17 Model: Make loading use less VRAM kingbri 2024-02-06 22:29:56 -05:00
  • fedebadc81 Model: Fix generate window fallback kingbri 2024-02-06 14:48:42 -05:00
  • 543a9b68c8 Requirements: Update Exllamav2 to 0.0.13.post1 kingbri 2024-02-04 21:25:57 -05:00
  • f10a5cfee6 Auth: Create keys on different exception kingbri 2024-02-04 01:56:42 -05:00
  • fa2acb2828
    Adds aliases for min_temp and max_temp (#58) erinmaybe 2024-02-03 21:51:29 -05:00
  • a769d90bad Args: Fix developer group kingbri 2024-02-03 00:16:47 -05:00
  • f1ea15d77e Model: Remove backwards compatability hacks kingbri 2024-02-02 23:40:10 -05:00
  • 6eeb62b82c Requirements: Update exllamav2, torch, and FA2 kingbri 2024-02-02 22:24:44 -05:00
  • 1919bf7705 Launch: Make exllamav2 requirement more friendly kingbri 2024-02-02 22:04:35 -05:00
  • b827bcbb44 Sampling: Cleanup and update kingbri 2024-02-01 12:58:55 -05:00
  • 2ea063cea9 Tree: Require exllamav2 version for startup kingbri 2024-02-01 12:40:24 -05:00
  • d3781920b3 OAI: Split up utility functions kingbri 2024-02-01 00:26:42 -05:00
  • 634d299fd9 Sampling: Fix smoothing factor default fallback kingbri 2024-02-02 23:35:15 -05:00
  • d7c18855e7
    added quadratic sampling (#56) Alexander Abushady 2024-02-02 22:12:59 -05:00
  • 4a7b8b1b7a Samplers: Add dynamic temperature kingbri 2024-01-31 01:20:59 -05:00
  • 3605067898 Requirements: Don't use torch 2.2 kingbri 2024-01-29 23:30:10 -05:00
  • 751627e571 OAI: Add fasttensors to model load endpoint kingbri 2024-01-25 01:01:29 -05:00
  • fc4570220c API + Model: Add new parameters and clean up documentation kingbri 2024-01-25 00:11:30 -05:00
  • 90fb41a77a Model: Fix prompt template initialization kingbri 2024-01-24 23:36:35 -05:00
  • 740b0215dd Model: Dynamically scale generate_window kingbri 2024-01-24 01:26:38 -05:00
  • 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