Skill · em Dados, IA e pesquisa
long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings,…
Procedência
- Origem: davila7/claude-code-templates
- Caminho:
cli-tool/components/skills/ai-research/emerging-techniques-long-context - Versão fixada:
57f899e5394bb8ca166f38eacae8f0853cbfe033 - Licença: MIT
- Espelhado em 25/09/2026
- 2 downloads no Claude Code Templates (lido em 25/09/2026)
Antes de instalar
4 arquivos · 57,3 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/long-context/.
d=".claude/skills/long-context" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-long-context" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/extension_methods.md" "$u/references/extension_methods.md" \ -o "$d/references/fine_tuning.md" "$u/references/fine_tuning.md" \ -o "$d/references/rope.md" "$u/references/rope.md"
Global: instala em ~/.claude/skills/long-context/.
d="$HOME/.claude/skills/long-context" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-long-context" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/extension_methods.md" "$u/references/extension_methods.md" \ -o "$d/references/fine_tuning.md" "$u/references/fine_tuning.md" \ -o "$d/references/rope.md" "$u/references/rope.md"
Codex
Neste projeto: instala em .agents/skills/long-context/.
d=".agents/skills/long-context" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-long-context" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/extension_methods.md" "$u/references/extension_methods.md" \ -o "$d/references/fine_tuning.md" "$u/references/fine_tuning.md" \ -o "$d/references/rope.md" "$u/references/rope.md"
Global: instala em ~/.agents/skills/long-context/.
d="$HOME/.agents/skills/long-context" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-long-context" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/extension_methods.md" "$u/references/extension_methods.md" \ -o "$d/references/fine_tuning.md" "$u/references/fine_tuning.md" \ -o "$d/references/rope.md" "$u/references/rope.md"
Antigravity
Neste projeto: instala em .agents/skills/long-context/.
d=".agents/skills/long-context" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-long-context" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/extension_methods.md" "$u/references/extension_methods.md" \ -o "$d/references/fine_tuning.md" "$u/references/fine_tuning.md" \ -o "$d/references/rope.md" "$u/references/rope.md"
Global: instala em ~/.gemini/antigravity-cli/skills/long-context/.
d="$HOME/.gemini/antigravity-cli/skills/long-context" u="https://raw.githubusercontent.com/davila7/claude-code-templates/57f899e5394bb8ca166f38eacae8f0853cbfe033/cli-tool/components/skills/ai-research/emerging-techniques-long-context" curl -fsSL --create-dirs \ -o "$d/SKILL.md" "$u/SKILL.md" \ -o "$d/references/extension_methods.md" "$u/references/extension_methods.md" \ -o "$d/references/fine_tuning.md" "$u/references/fine_tuning.md" \ -o "$d/references/rope.md" "$u/references/rope.md"
Peça ao Rook
Já usa o Rook Labs? Cole no chat do Rook: instale a skill https://rooklabs.sh/marketplace/cct.long-context
Prévia do SKILL.md
---
name: long-context
description: Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attentio…
version: 1.0.0
author: Orchestra Research
license: MIT
tags: [Emerging Techniques, Long Context, RoPE, YaRN, ALiBi, Position Interpolation, Extended Context, Rotary Embeddings, Attention Bias, Context Extension, Positional Encoding]
dependencies: [transformers, torch, flash-attn]
---
# Long Context: Extending Transformer Context Windows
## When to Use This Skill
Use Long Context techniques when you need to:
- **Process long documents** (32k, 64k, 128k+ tokens) with transformer models
- **Extend context windows** of pre-trained models (LLaMA, Mistral, etc.)
- **Implement efficient positional encodings** (RoPE, ALiBi)
- **Train models** with length extrapolation capabilities
- **Deploy models** that handle variable-length inputs efficiently
- **Fine-tune** existing models for longer contexts with minimal compute
**Key Techniques**: RoPE (Rotary Position Embeddings), YaRN, ALiBi (Attention with Linear Biases), Position Interpolation
**Papers**: RoFormer (arXiv 2104.09864), YaRN (arXiv 2309.00071), ALiBi (arXiv 2108.12409), Position Interpolation (arXiv 2306.15595)
## Installation
```bash
# HuggingFace Transformers (includes RoPE, YaRN support)
pip install transformers torch
# For custom implementations
pip install einops # Tensor operations
pip install rotary-embedding-torch # Standalone RoPE
# Optional: FlashAttention for efficiency
pip install flash-attn --no-build-isolation
```
…