ros/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-01-30 04:22:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

typo in comments: change "GAPO" to "DAPO"

Browse Source
This commit is contained in:
Haoyu Wang
2026-01-16 01:03:42 -05:00
committed by GitHub
parent fbf2bbea25
commit 50413d2d67
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
scripts/chat_rl.py
View File

@@ -6,7 +6,7 @@ simpler and more similar to just REINFORCE:
1) Delete trust region, so there is no KL regularization to a reference model
2) We are on policy, so there's no need for PPO ratio+clip.
3) We use GAPO style normalization that is token-level, not sequence-level.
3) We use DAPO style normalization that is token-level, not sequence-level.
4) Instead of z-score normalization (r - mu)/sigma, only use (r - mu) as the advantage.
1 GPU: