Commit Graph

145 Commits

Author SHA1 Message Date
290c718187 Added qwq inference notebook 2025-03-30 09:26:18 +02:00
30eb5c419d Updated QwQ train notebook 2025-03-29 11:03:53 +00:00
585f655ad3 Better error handling when sourcing bootstrap script 2025-03-29 10:38:25 +01:00
56242496bb Add support for jupyter notebooks for training 2025-03-28 16:10:43 +00:00
468ef2ae1f configure git username and email in bootstrap script 2025-03-28 15:09:37 +00:00
Niels Geens
4ce27f6798 Switched to vscode server image 2025-03-28 15:43:54 +01:00
Niels Geens
606611d3ad Merge branch 'master' of https://git.nielsgeens.be/llm/SIA 2025-03-28 15:31:20 +01:00
Niels Geens
dd6fec8391 Switched to larger gpu 2025-03-28 15:31:00 +01:00
8975a54d58 WIP QwQ train 2025-03-24 15:46:54 +00:00
1ef32ed33e WIP manual implementation of QwQ finetune 2025-03-24 12:05:43 +00:00
3594c8150a WIP Simplify training 2025-03-24 10:53:51 +00:00
Niels Geens
8d9d3ca576 Use PAT to authenticate 2025-03-20 14:42:42 +01:00
9a171ab622 Fixes for QwQ training 2025-03-20 09:41:02 +01:00
Niels Geens
92b0ff3aa0 Increased runpod volume size 2025-03-18 09:53:15 +01:00
Niels Geens
3ea5ba87a9 Fix venv add to path 2025-03-18 09:46:16 +01:00
Niels Geens
5c1ef4d9e7 More improvements to bootstrap 2025-03-17 10:38:36 +01:00
Niels Geens
2d655781c8 Fixed github_keys and deploy scripts 2025-03-17 10:14:41 +01:00
Niels Geens
d5a5fd1071 Simplified bootstrapping 2025-03-14 15:53:27 +01:00
Niels Geens
5c95a8482f Added script to start runpod 2025-03-14 11:22:45 +01:00
Niels Geens
2e66020f8e Replaced deepseek with qwq 2025-03-14 11:22:30 +01:00
Niels Geens
3ea3239a9b wip deepseek train 2025-03-03 16:57:04 +01:00
b64f8d7d33 wip deepseek r1 2025-03-02 22:01:24 +01:00
b7e95d7398 Added restart script and fixed dockerfile and run to match docs 2025-03-01 13:29:17 +01:00
Niels Geens
1d5b687e00 Improved collect script with better filtering 2025-02-27 17:09:38 +01:00
Niels Geens
979932ddab Added info about filesystem, tools and git as procedures 2025-02-26 18:16:28 +01:00
Niels Geens
a536134040 Merge branch 'master' of https://git.nielsgeens.be/llm/SIA 2025-02-24 14:05:43 +01:00
Niels Geens
f635725064 Improved self improvement example directory structure 2025-02-24 14:05:32 +01:00
Niels Geens
d51b0d5582 Improved self improvement example directory structure 2025-02-24 14:03:52 +01:00
Niels Geens
e664c625b7 Cleanup of self_improvement reasoning.md 2025-01-31 13:06:09 +01:00
Niels Geens
ae34c070a0 Added info about results and metrics for challenges 2025-01-24 14:47:09 +01:00
Niels Geens
1cd483fd3a Improved self improvement finetune info 2025-01-24 11:41:02 +01:00
Niels Geens
4fcb32e6a1 Added tool for finetuning mistral model based on training config 2025-01-24 11:05:23 +01:00
Niels Geens
1ee8cbc75c Initial training config file 2025-01-24 10:55:56 +01:00
Niels Geens
cab452c614 Restructured self improvement reasoning + added training data 2025-01-23 15:51:25 +01:00
Niels Geens
69d7c6b605 merged reasoning for self improvement 2025-01-23 11:44:55 +01:00
Niels Geens
f152914431 added to wip self improvement 2025-01-20 16:51:09 +01:00
c3846ac39f Merge branch 'master' of https://git.nielsgeens.be/llm/SIA 2025-01-19 22:39:04 +01:00
b6a4a5adae WIP self improvement procedure 2025-01-19 22:38:47 +01:00
3058820668 Merge branch 'master' of https://git.nielsgeens.be/llm/SIA 2025-01-16 14:37:10 +01:00
fffdefcd92 More updates to itb (wip) 2025-01-16 14:36:37 +01:00
e60d5baeca Look for iterations recursively 2025-01-16 14:35:26 +01:00
3ab726f961 Properly close mistral response 2025-01-09 20:01:32 +01:00
Niels Geens
ed9e38c848 Fix /] in mermaid diagram 2025-01-08 22:49:29 +01:00
Niels Geens
9d0430400c Fixed mermaid newlines 2025-01-08 22:47:50 +01:00
Niels Geens
4cd0fe8450 Added first procedures 2025-01-08 22:42:14 +01:00
Niels Geens
e730eba58c Fix error in "fixed" timestamps 2025-01-06 14:15:32 +01:00
Niels Geens
6669b7a682 Fixed timestamp timezone for entry id's 2025-01-02 16:52:43 +01:00
e0bc7a7159 Update to itb_screenshot and friends 2024-12-27 17:07:19 +01:00
fe72969b4f Cleanup of itb readme 2024-12-26 18:19:27 +01:00
63d1264f5a Continue work on itb 2024-12-26 17:36:59 +01:00