DL Coding

Post-Training and Alignment

Name: TensorTonic
Author: TensorTonic

GRPO, PPO, DPO, and RLHF foundations: losses, advantages, and reward modeling primitives.

Upgrade to Pro to take any set.

30 min

Set 1Problems

1Sequence Log Probabilityeasy

2GRPO Clipped Surrogate Lossmedium

3PPO Value Function Losseasy