要理解 LLM,必须读的论文顺序:
1. Attention Is All You Need(Transformers)
2. GPT-2(Scaling + Zero-shot)
3. Scaling Laws(Kaplan, 2020)
4. GPT-3(Few-shot)
5. Chinchilla(Data Needed)
6. InstructGPT(RLHF)
7. LoRA(Fine-Tuning w/o Broken)
8. FlashAttention(Fast)
9. Chain-of-Thought(Reasoning)
10. DPO(RLHF w/o Pain)
显示更多