Skill · em Dados, IA e pesquisa

peft-fine-tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with…

Procedência

Antes de instalar

3 arquivos · 34,3 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/peft-fine-tuning/.

d=".claude/skills/peft-fine-tuning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/fine-tuning-peft"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Global: instala em ~/.claude/skills/peft-fine-tuning/.

d="$HOME/.claude/skills/peft-fine-tuning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/fine-tuning-peft"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Codex

Neste projeto: instala em .agents/skills/peft-fine-tuning/.

d=".agents/skills/peft-fine-tuning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/fine-tuning-peft"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Global: instala em ~/.agents/skills/peft-fine-tuning/.

d="$HOME/.agents/skills/peft-fine-tuning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/fine-tuning-peft"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Antigravity

Neste projeto: instala em .agents/skills/peft-fine-tuning/.

d=".agents/skills/peft-fine-tuning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/fine-tuning-peft"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Global: instala em ~/.gemini/antigravity-cli/skills/peft-fine-tuning/.

d="$HOME/.gemini/antigravity-cli/skills/peft-fine-tuning"
u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/fine-tuning-peft"
curl -fsSL --create-dirs \
  -o "$d/SKILL.md" "$u/SKILL.md" \
  -o "$d/references/advanced-usage.md" "$u/references/advanced-usage.md" \
  -o "$d/references/troubleshooting.md" "$u/references/troubleshooting.md"

Peça ao Rook

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

Prévia do SKILL.md

---
name: peft-fine-tuning
description: Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers eco…
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Fine-Tuning, PEFT, LoRA, QLoRA, Parameter-Efficient, Adapters, Low-Rank, Memory Optimization, Multi-Adapter]
dependencies: [peft>=0.13.0, transformers>=4.45.0, torch>=2.0.0, bitsandbytes>=0.43.0]
---

# PEFT (Parameter-Efficient Fine-Tuning)

Fine-tune LLMs by training <1% of parameters using LoRA, QLoRA, and 25+ adapter methods.

## When to use PEFT

**Use PEFT/LoRA when:**
- Fine-tuning 7B-70B models on consumer GPUs (RTX 4090, A100)
- Need to train <1% parameters (6MB adapters vs 14GB full model)
- Want fast iteration with multiple task-specific adapters
- Deploying multiple fine-tuned variants from one base model

**Use QLoRA (PEFT + quantization) when:**
- Fine-tuning 70B models on single 24GB GPU
- Memory is the primary constraint
- Can accept ~5% quality trade-off vs full fine-tuning

**Use full fine-tuning instead when:**
- Training small models (<1B parameters)
- Need maximum quality and have compute budget
- Significant domain shift requires updating all weights

## Quick start

### Installation

```bash
# Basic installation
pip install peft
…

Ver todo o marketplace