Fine-tuning LLMs on Human Feedback (RLHF + DPO) скачать в хорошем качестве

Fine-tuning LLMs on Human Feedback (RLHF + DPO)

🤝 Work with me: https://www.shawhintalebi.com 🚀 Ship AI apps in weeks, not months: https://aibuilder.academy/yt/bbVoDXoPrPM Here, I discuss how to use reinforcement learning to fine-tune LLMs on human feedback (i.e. RLHF) and a more efficient reformulation of it (i.e. DPO) 📰 Read more: https://medium.com/@shawhin/fine-tuni... Example code: https://github.com/ShawhinT/YouTube-B... 🤗 Dataset: https://huggingface.co/datasets/shawh... 🤗 Fine-tuned Model: https://huggingface.co/shawhin/Qwen2.... References [1] arXiv:2407.21783 [cs.AI] [2] arXiv:2203.02155 [cs.CL] [3] arXiv:1707.06347 [cs.LG] [4]    • Deep Dive into LLMs like ChatGPT   [5] arXiv:2305.18290 [cs.LG] Intro - 0:00 Base Models - 0:25 InstructGPT - 2:20 RL from Human Feedback (RLHF) - 5:18 Proximal Policy Optimization (PPO) - 9:20 Limitations of RLHF - 10:30 Direct Policy Optimization (DPO) - 11:50 Example: Fine-tuning Qwen on Title Preferences - 14:29 Step 1: Curate preference data - 17:49 Step 2: Fine-tuning with DPO - 20:53 Step 3: Evaluate fine-tuning model - 25:27