local-distillation-lab
OfficialOn-device local distillation evaluation.
Software Engineering#evaluation#fine-tuning#on-device#reinforcement-learning#distillation#local-distillation#pedagogical-arm
Authorunderstudylabs
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This skill helps developers fine-tune or distill a local open model on their Mac and compare methods to see which training approach actually improves a captured workload.
Core Features & Use Cases
- On-device local-distillation workflows to compare baseline, rejection-sampled fine-tuning, distillation, and pedagogical arms.
- Safety and privacy by keeping all training and evaluation local.
- Use cases include evaluating improvements on a captured workload with privileged context without hosted RL.
Quick Start
Run the local distillation lab to start a controlled, on-device comparison of training methods using your own dataset.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: local-distillation-lab Download link: https://github.com/understudylabs/understudy-agent-tools/archive/main.zip#local-distillation-lab Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.