Skill · em Dados, IA e pesquisa

model-pruning

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M…

Procedência

Antes de instalar

2 arquivos · 22,7 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/model-pruning/.

d=".claude/skills/model-pruning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-model-pruning"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/wanda.md" "$u/references/wanda.md"

Global: instala em ~/.claude/skills/model-pruning/.

d="$HOME/.claude/skills/model-pruning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-model-pruning"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/wanda.md" "$u/references/wanda.md"

Codex

Neste projeto: instala em .agents/skills/model-pruning/.

d=".agents/skills/model-pruning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-model-pruning"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/wanda.md" "$u/references/wanda.md"

Global: instala em ~/.agents/skills/model-pruning/.

d="$HOME/.agents/skills/model-pruning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-model-pruning"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/wanda.md" "$u/references/wanda.md"

Antigravity

Neste projeto: instala em .agents/skills/model-pruning/.

d=".agents/skills/model-pruning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-model-pruning"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/wanda.md" "$u/references/wanda.md"

Global: instala em ~/.gemini/antigravity-cli/skills/model-pruning/.

d="$HOME/.gemini/antigravity-cli/skills/model-pruning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-model-pruning"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/wanda.md" "$u/references/wanda.md"

Peça ao Rook

Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.model-pruning

Prévia do SKILL.md

---
name: model-pruning
description: Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity…
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Emerging Techniques, Model Pruning, Wanda, SparseGPT, Sparsity, Model Compression, N:M Sparsity, One-Shot Pruning, Structured Pruning, Unstructured Pruning, Fast Inference]
dependencies: [transformers, torch]
---

# Model Pruning: Compressing LLMs

## When to Use This Skill

Use Model Pruning when you need to:
- **Reduce model size** by 40-60% with <1% accuracy loss
- **Accelerate inference** using hardware-friendly sparsity (2-4× speedup)
- **Deploy on constrained hardware** (mobile, edge devices)
- **Compress without retraining** using one-shot methods
- **Enable efficient serving** with reduced memory footprint

**Key Techniques**: Wanda (weights × activations), SparseGPT (second-order), structured pruning, N:M sparsity

**Papers**: Wanda ICLR 2024 (arXiv 2306.11695), SparseGPT (arXiv 2301.00774)

## Installation

```bash
# Wanda implementation
git clone https://github.com/locuslab/wanda
cd wanda
pip install -r requirements.txt

# Optional: SparseGPT
git clone https://github.com/IST-DASLab/sparsegpt
cd sparsegpt
pip install -e .

# Dependencies
pip install torch transformers accelerate
…

Ver todo o marketplace