X · @teortaxesTex
· X / Twitter
The plot thickens! I guess Tianhang can boast of his RL contributions very legitimately. PPO back then was a really high-risk, high-effort choice. I a…
The plot thickens! I guess Tianhang can boast of his RL contributions very legitimately. PPO back then was a really high-risk, high-effort choice. I apologize.Zheng Yuan: @ChujieZheng Tianhang is the first guy who successfully training first-gen Qwen with PPO and show descent performance improvement.