Generative AI/Fine-tuning
- LLM Twin 프로젝트로 설명하는 SFT (Supervised FIne-tuning) 2025.02.18
- LIMA: Less Is More for Alignment 2025.01.22
- Scaling Relationship On Learning Mathematical Reasoning with Large Language Models 2025.01.22
- Beyond Human Data: Scaling Self-Training forProblem-Solving with Language Models 2025.01.22
- Reinforced Self-Training (ReST) for Language Modeling 2025.01.22
- Magicoder: Empowering Code Generation with OSS-INSTRUCT 2025.01.22
- WizardLM: Empowering Large Language Models toFollow Complex Instructions 2025.01.21
- Fine-tuned Language Models are Zero-shot Learners 2025.01.20
- SELF-INSTRUCT: Aligning Language Models with Self-Generated Instructions 2025.01.19
- Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models 2025.01.16