Commit Graph

  • 9c2d38e1a6 Fix install script, use correct venvs for jupyter Niels Geens 2025-04-07 11:36:41 +02:00
  • ead5c35a09 Added rust dependency to docker build Geens 2025-04-06 22:41:34 +02:00
  • 192ade72ee Fixed build on cloud Niels Geens 2025-04-06 14:46:42 +00:00
  • ea93adc4c8 Fix dockerfile for xml schema validator Geens 2025-04-06 16:11:36 +02:00
  • 55a920414d Begin XML Schema Validator Geens 2025-04-05 23:15:39 +02:00
  • 0e2cca2e4f Fixed QwQ tokenizer Niels Geens 2025-04-04 08:54:06 +00:00
  • 156d3aa7d3 Bootstrapping QwQ works!! Niels Geens 2025-04-02 16:37:17 +00:00
  • b4c08586ee Applied add_venvs_to_path.sh script to local runs Niels Geens 2025-04-02 18:05:48 +02:00
  • ed37792b62 Better path fix Niels Geens 2025-04-02 15:58:30 +00:00
  • ea22e1527e Fix bug where runpod environment file overwrites PATH Niels Geens 2025-04-02 14:47:33 +00:00
  • e573b9ebe7 Removed flash-attn as dependency because it's hard to install properly Niels Geens 2025-04-02 14:42:35 +02:00
  • 78c71ab8b4 Improved install experience Niels Geens 2025-04-01 15:26:50 +00:00
  • c00256f723 Clean up install script Niels Geens 2025-04-01 16:30:42 +02:00
  • 130afbdd92 Updates after testing Niels Geens 2025-04-01 11:49:21 +00:00
  • 6f3d414d17 Converted QwQ notebooks to .py files Niels Geens 2025-04-01 10:41:24 +02:00
  • 642c5181bb Fixed inference notebook Niels Geens 2025-03-30 08:52:17 +00:00
  • 290c718187 Added qwq inference notebook Geens 2025-03-30 09:26:18 +02:00
  • 30eb5c419d Updated QwQ train notebook Niels Geens 2025-03-29 11:03:53 +00:00
  • 585f655ad3 Better error handling when sourcing bootstrap script Geens 2025-03-29 10:38:25 +01:00
  • 56242496bb Add support for jupyter notebooks for training Niels Geens 2025-03-28 16:10:43 +00:00
  • 468ef2ae1f configure git username and email in bootstrap script Niels Geens 2025-03-28 15:09:37 +00:00
  • 4ce27f6798 Switched to vscode server image Niels Geens 2025-03-28 15:43:54 +01:00
  • 606611d3ad Merge branch 'master' of https://git.nielsgeens.be/llm/SIA Niels Geens 2025-03-28 15:31:20 +01:00
  • dd6fec8391 Switched to larger gpu Niels Geens 2025-03-28 15:31:00 +01:00
  • 8975a54d58 WIP QwQ train Niels Geens 2025-03-24 15:46:54 +00:00
  • 1ef32ed33e WIP manual implementation of QwQ finetune Niels Geens 2025-03-24 12:05:43 +00:00
  • 3594c8150a WIP Simplify training Niels Geens 2025-03-24 10:53:51 +00:00
  • 8d9d3ca576 Use PAT to authenticate Niels Geens 2025-03-20 14:42:42 +01:00
  • 9a171ab622 Fixes for QwQ training Geens 2025-03-20 09:41:02 +01:00
  • 92b0ff3aa0 Increased runpod volume size Niels Geens 2025-03-18 09:53:15 +01:00
  • 3ea5ba87a9 Fix venv add to path Niels Geens 2025-03-18 09:46:16 +01:00
  • 5c1ef4d9e7 More improvements to bootstrap Niels Geens 2025-03-17 10:38:36 +01:00
  • 2d655781c8 Fixed github_keys and deploy scripts Niels Geens 2025-03-17 10:14:41 +01:00
  • d5a5fd1071 Simplified bootstrapping Niels Geens 2025-03-14 15:53:27 +01:00
  • 5c95a8482f Added script to start runpod Niels Geens 2025-03-14 11:22:45 +01:00
  • 2e66020f8e Replaced deepseek with qwq Niels Geens 2025-03-14 11:22:30 +01:00
  • 3ea3239a9b wip deepseek train Niels Geens 2025-03-03 16:57:04 +01:00
  • b64f8d7d33 wip deepseek r1 Geens 2025-03-02 22:01:24 +01:00
  • b7e95d7398 Added restart script and fixed dockerfile and run to match docs Geens 2025-03-01 13:29:17 +01:00
  • 1d5b687e00 Improved collect script with better filtering Niels Geens 2025-02-27 17:09:38 +01:00
  • 979932ddab Added info about filesystem, tools and git as procedures Niels Geens 2025-02-26 18:16:28 +01:00
  • a536134040 Merge branch 'master' of https://git.nielsgeens.be/llm/SIA Niels Geens 2025-02-24 14:05:43 +01:00
  • f635725064 Improved self improvement example directory structure Niels Geens 2025-02-24 14:03:52 +01:00
  • d51b0d5582 Improved self improvement example directory structure Niels Geens 2025-02-24 14:03:52 +01:00
  • e664c625b7 Cleanup of self_improvement reasoning.md Niels Geens 2025-01-31 13:06:09 +01:00
  • ae34c070a0 Added info about results and metrics for challenges Niels Geens 2025-01-24 14:47:09 +01:00
  • 1cd483fd3a Improved self improvement finetune info Niels Geens 2025-01-24 11:41:02 +01:00
  • 4fcb32e6a1 Added tool for finetuning mistral model based on training config Niels Geens 2025-01-24 11:05:23 +01:00
  • 1ee8cbc75c Initial training config file Niels Geens 2025-01-24 10:41:56 +01:00
  • cab452c614 Restructured self improvement reasoning + added training data Niels Geens 2025-01-23 15:51:25 +01:00
  • 69d7c6b605 merged reasoning for self improvement Niels Geens 2025-01-23 11:44:55 +01:00
  • f152914431 added to wip self improvement Niels Geens 2025-01-20 16:51:09 +01:00
  • c3846ac39f Merge branch 'master' of https://git.nielsgeens.be/llm/SIA Geens 2025-01-19 22:39:04 +01:00
  • b6a4a5adae WIP self improvement procedure Geens 2025-01-19 22:38:47 +01:00
  • 3058820668 Merge branch 'master' of https://git.nielsgeens.be/llm/SIA geens 2025-01-16 14:37:10 +01:00
  • fffdefcd92 More updates to itb (wip) geens 2025-01-16 14:36:37 +01:00
  • e60d5baeca Look for iterations recursively geens 2025-01-16 14:35:26 +01:00
  • 3ab726f961 Properly close mistral response Geens 2025-01-09 20:01:32 +01:00
  • ed9e38c848 Fix /] in mermaid diagram Niels Geens 2025-01-08 22:49:29 +01:00
  • 9d0430400c Fixed mermaid newlines Niels Geens 2025-01-08 22:47:50 +01:00
  • 4cd0fe8450 Added first procedures Niels Geens 2025-01-08 22:42:14 +01:00
  • e730eba58c Fix error in "fixed" timestamps Niels Geens 2025-01-06 14:15:32 +01:00
  • 6669b7a682 Fixed timestamp timezone for entry id's Niels Geens 2025-01-02 16:52:43 +01:00
  • e0bc7a7159 Update to itb_screenshot and friends geens 2024-12-27 17:07:19 +01:00
  • fe72969b4f Cleanup of itb readme geens 2024-12-26 18:19:27 +01:00
  • 63d1264f5a Continue work on itb geens 2024-12-26 17:36:59 +01:00
  • eadd4eeabe Merge branch 'master' of https://git.nielsgeens.be/llm/SIA geens 2024-12-18 15:49:26 +01:00
  • cdd0c701f9 WIP itb_click Niels Geens 2024-12-13 10:33:52 +01:00
  • 2499d7b83f Added itb_scroll geens 2024-12-08 10:54:37 +01:00
  • 928c1e14b9 First version of itb_screenshot geens 2024-12-08 10:40:28 +01:00
  • 6ab61ed384 ITB WIP Niels Geens 2024-12-08 09:51:43 +01:00
  • da8583ab28 ITP WiP geens 2024-12-04 17:19:46 +01:00
  • af390dd779 Merge branch 'master' of https://git.nielsgeens.be/llm/SIA geens 2024-12-04 11:42:33 +01:00
  • 56563d7c72 Added example scripts for using selenium Niels Geens 2024-12-03 13:45:17 +01:00
  • be81d117ac Added init flag to docker run to handle defunct processes Niels Geens 2024-12-03 12:25:06 +01:00
  • bad926089d Start work on ITB and webbrowsing geens 2024-12-01 15:07:23 +01:00
  • e71bd7e9eb Allow stopping of inference geens 2024-11-30 12:44:13 +01:00
  • a0353d0d49 Removed old iterations geens 2024-11-24 20:38:01 +01:00
  • a9e70f0a22 Added iteration loading geens 2024-11-24 20:35:28 +01:00
  • b6c1a95abd Added memory editing functionality geens 2024-11-24 18:00:27 +01:00
  • 2c820f6ead WIP memory editor geens 2024-11-23 21:36:50 +01:00
  • dbc0068a82 Server side implementation for interactive entry edits geens 2024-11-23 15:34:33 +01:00
  • bb74fd3621 Added output length on truncated scripts geens 2024-11-23 09:36:34 +01:00
  • d9d7773369 Fixed transparant background in select component geens 2024-11-22 18:58:24 +01:00
  • cd713fd09e Removed todo geens 2024-11-22 18:53:23 +01:00
  • 5aa2383f26 Fixed autoscroll with small delay geens 2024-11-22 18:50:47 +01:00
  • eb89564aac autoscroll wip Niels Geens 2024-11-22 17:43:23 +01:00
  • 69f4f8a6fc Fixed auto approver Niels Geens 2024-11-22 17:11:06 +01:00
  • 8766a945c0 Enable multiple llms Niels Geens 2024-11-22 15:05:54 +01:00
  • bbb88f39e8 Added another set of iterations Niels Geens 2024-11-20 16:06:33 +01:00
  • 84228d56de Added dataset creator Niels Geens 2024-11-20 11:16:51 +01:00
  • 56d9d26c23 Cleaned up initial iteration Niels Geens 2024-11-20 10:38:48 +01:00
  • 03cf69d272 Added iteration_logger Niels Geens 2024-11-19 20:24:21 +01:00
  • ef94d0d1a0 Added mistral llm engine geens 2024-11-17 16:53:44 +01:00
  • 506bc91639 Added api token for local llm geens 2024-11-16 22:09:04 +01:00
  • 410e2b56f9 Fix timeout printing geens 2024-11-16 21:57:15 +01:00
  • c44d0ffbdf Fixes for runpod test geens 2024-11-16 21:51:18 +01:00
  • 9dfd5ddc39 Add auto_approver Niels Geens 2024-11-15 17:09:07 +01:00
  • 4ce421bbce Fixed context usage calculation Niels Geens 2024-11-14 18:23:33 +01:00
  • ede0a642d3 Moved context generation to base agent instead of system_metrics Niels Geens 2024-11-14 14:51:54 +01:00