#rlhf

Explain LLM training, reinforcement learning and evaluation
ML designCohere
▲ 00 solutions
Post-train a 7B model to code better for one enterprise
ML designCohere
▲ 00 solutions
Reward-model RLHF versus direct preference optimization
ML designMistral AIGoogleMicrosoft
▲ 00 solutions
KL divergence in language models
ML designGoogle
▲ 00 solutions
Detect and prevent reward hacking
ML designGoogle
▲ 00 solutions
Design an LLM chatbot: training data, rewards and deployment
AI systemAmazon
▲ 00 solutions
GRPO in NumPy: group-relative advantages, process and shaped rewards
ML designAmazon
▲ 00 solutions
RLHF take-home aligning a small open model
CodingHugging Face
▲ 01 solution