Commit Graph

155 Commits

Author SHA1 Message Date
156d3aa7d3 Bootstrapping QwQ works!! 2025-04-02 16:37:17 +00:00
Niels Geens
b4c08586ee Applied add_venvs_to_path.sh script to local runs 2025-04-02 18:05:48 +02:00
ed37792b62 Better path fix 2025-04-02 15:58:30 +00:00
ea22e1527e Fix bug where runpod environment file overwrites PATH 2025-04-02 14:47:33 +00:00
Niels Geens
e573b9ebe7 Removed flash-attn as dependency because it's hard to install properly 2025-04-02 14:42:35 +02:00
78c71ab8b4 Improved install experience 2025-04-01 15:26:50 +00:00
Niels Geens
c00256f723 Clean up install script 2025-04-01 16:30:42 +02:00
130afbdd92 Updates after testing 2025-04-01 11:49:21 +00:00
Niels Geens
6f3d414d17 Converted QwQ notebooks to .py files 2025-04-01 10:42:54 +02:00
642c5181bb Fixed inference notebook 2025-03-30 08:52:17 +00:00
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