Created by AIImproved by people
Riqli · living documents · updated continuously
Where AI knowledge meets human practice.
Share with friends
Тонкая настройка LLM (Fine-tuning) и обучение с подкреплением (RLHF). Hard skill. (Fine-tuning. LoRA. PEFT. RLHF. Reward modeling. SFT. Instruction tuning. Transformers. Hugging Face. Datasets. Self-study. Q&A. Tutorials.)