Individual skill
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.
backend/cli/skills/ml-training/knowledge-distillation/SKILL.md
Source commit a08e0ad0ad3d6448123039ee4659163eb2e35d99
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 4,353
- Repository last updated
- Nov 6, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent Repository topic
- ai Repository topic
- bun Repository topic
- cli Repository topic
- llm Repository topic
- ml Repository topic
- open-source Repository topic
- research Repository topic
- science Repository topic
- ai-agent Repository topic
- emerging-techniques Declared skill tag
- knowledge-distillation Declared skill tag
- model-compression Declared skill tag
- teacher-student Declared skill tag
- minillm Declared skill tag
- reverse-kld Declared skill tag
- soft-targets Declared skill tag
- temperature-scaling Declared skill tag
- logit-distillation Declared skill tag
- model-transfer Declared skill tag
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesSKILL.mdcore · 13,943 bytesreferences/minillm.mddoc · 9,117 bytes
Read excerpt
# Knowledge Distillation: Compressing LLMs
## When to Use This Skill
Use Knowledge Distillation when you need to:
- **Compress models** from 70B → 7B while retaining 90%+ performance
- **Transfer capabilities** from proprietary models (GPT-4) to open-source (LLaMA, Mistral)
- **Reduce inference costs** by deploying smaller student models
- **Create specialized models** by distilling domain-specific knowledge
- **Improve small models** using synthetic data from large teachers
**Key Techniques**: Temperature scaling, soft targets, reverse KLD (MiniLLM), logit distillation, response distillation
**Papers**: Hinton et al. 2015 (arXiv 1503.02531), MiniLLM (arXiv 2306.08543), KD Survey (arXiv 2402.13116)