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, attention biases, interpolation methods, and extrapolation strategies for LLMs.
安装
npx skills add davila7/claude-code-templates --skill long-contextnpx skills add davila7/claude-code-templates --skill long-context -a claude-code -gnpx skills add davila7/claude-code-templates --skill long-context -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/emerging-techniques-long-contextgh skill install davila7/claude-code-templates long-contextgit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/emerging-techniques-long-context ~/.claude/skills/long-context # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/emerging-techniques-long-context ~/.agents/skills/long-context # Codex, Cursor, Gemini CLI, Copilot, OpenCode