Skill · em Dados, IA e pesquisa
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…
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/skills/ai-research/emerging-techniques-knowledge-distillation - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- 3 downloads no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
2 arquivos · 22,2 KB · só texto, nenhum script
Instalar na sua CLI
O comando baixa a versão fixada (commit 57f899e) direto da origem, para a pasta que a CLI lê. Precisa de curl (macOS e Linux); no Windows não há comando, porque o Rook Labs é para macOS.
Claude Code
Neste projeto: instala em .claude/skills/knowledge-distillation/.
d=".claude/skills/knowledge-distillation" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-knowledge-distillation" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/minillm.md" "$u/references/minillm.md"
Global: instala em ~/.claude/skills/knowledge-distillation/.
d="$HOME/.claude/skills/knowledge-distillation" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-knowledge-distillation" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/minillm.md" "$u/references/minillm.md"
Codex
Neste projeto: instala em .agents/skills/knowledge-distillation/.
d=".agents/skills/knowledge-distillation" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-knowledge-distillation" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/minillm.md" "$u/references/minillm.md"
Global: instala em ~/.agents/skills/knowledge-distillation/.
d="$HOME/.agents/skills/knowledge-distillation" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-knowledge-distillation" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/minillm.md" "$u/references/minillm.md"
Antigravity
Neste projeto: instala em .agents/skills/knowledge-distillation/.
d=".agents/skills/knowledge-distillation" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-knowledge-distillation" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/minillm.md" "$u/references/minillm.md"
Global: instala em ~/.gemini/antigravity-cli/skills/knowledge-distillation/.
d="$HOME/.gemini/antigravity-cli/skills/knowledge-distillation" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-knowledge-distillation" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/minillm.md" "$u/references/minillm.md"
Peça ao Rook
Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.knowledge-distillation
Prévia do SKILL.md
---
name: knowledge-distillation
description: 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 distillat…
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Emerging Techniques, Knowledge Distillation, Model Compression, Teacher-Student, MiniLLM, Reverse KLD, Soft Targets, Temperature Scaling, Logit Distillation, Model Transfer]
dependencies: [transformers, torch, datasets]
---
# 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)
## Installation
```bash
# Standard transformers
pip install transformers datasets accelerate
# For training
pip install torch deepspeed wandb
# Optional: MiniLLM implementation
git clone https://github.com/microsoft/LMOps
cd LMOps/minillm
pip install -e .
```
…