Sponsored:
If someone googles you right now and you don’t come up? You might as well not exist. Every client, opportunity and connection is passing you by.
You don’t need to know code. RoseHosting lets you launch something you’re proud of this afternoon.
Stop hiding. Build yours today.
Video by Hugging Face via YouTube
In this live session, we’ll cover how to transfer capability from a teacher model to a smaller student through distillation. We’ll work through supervised fine-tuning on teacher-generated data, then on-policy and online methods where the teacher scores the student live, then self-distillation where the model teaches itself. Each one runs in TRL.
What we’ll cover:
– What distillation is, and the four axes that organize it: signal, data source, timing, and teacher identity
– White-box vs black-box: distilling from open weights vs strings
– Off-policy distillation: generate from the teacher, then SFT on the outputs
– On-policy distillation: sample from the student, score with the teacher in the loop
– Distillation as reinforcement learning: the KD distance as a dense, token-level reward
– Self-distillation: the model as its own teacher, and when that beats a stronger one
Repo: https://github.com/burtenshaw/training-agents
This is part of the Training Agents series: using coding agents to design, run, monitor, and review post-training experiments, while training models to become better agents.
#TRL #HuggingFace #PostTraining #AIAgents #Distillation