Agent Skills: emerging-techniques-knowledge-distillation

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

ID: davila7/claude-code-templates/emerging-techniques-knowledge-distillation

Install this agent skill to your local

npx skills add davila7/claude-code-templates --skill emerging-techniques-knowledge-distillation

Skill Files

The files that make up emerging-techniques-knowledge-distillation.

Download Skill

More agent skills