The Fine-Tuning Index / RLHF & Preference / #32

laoshan-song/Awesome-LLM-Interview

by laoshan-song · RLHF & Preference · updated 3d ago

LLM interview prep notes: Transformer, RLHF, DPO, LoRA, KV Cache,RAG, MoE, distributed training & 2026 frontier topics

66
momentum
120
stars
5
forks
#32
rank
View on GitHub →