Long Context

orchestra-research/ai-research-skills/19-emerging-techniques/long-context

by orchestra-research773a52944ba4MIT13K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 3 months ago

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.

Instructions onlyAI & Agents

Only the file list is public. File contents are available once the skill is installed in a workspace.

PathSizeType
references/extension_methods.md14.2 KBtext/markdown
references/fine_tuning.md16 KBtext/markdown
references/rope.md11.8 KBtext/markdown
SKILL.md15.2 KBtext/markdown

Source and attribution

Source:orchestra-research/ai-research-skillsin19-emerging-techniques/long-contextat commit773a529

License: MIT

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal