↓ 1 callersFunctionrlhf_loop(w, updates=300, beta=0.1, lr=0.05, eps=0.2, rng=None)
phases/09-reinforcement-learning/09-reward-modeling-rlhf/code/main.py:90
↓ 1 callersFunctionroute(input_text: str, classifier: Callable[[str], str],
handlers: dict[str, Callable[[str], str]])
phases/14-agent-engineering/12-anthropic-workflow-patterns/code/main.py:45
↓ 1 callersFunctionrun_config(
effective_batch: int,
accum_steps: int,
*,
in_dim: int,
hidden: int,
out_dim: int,
phases/19-capstone-projects/46-gradient-accumulation/code/main.py:151