Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Extending the context window of a Transformer v1.0.0

Use this resource to extend a model's context window with RoPE, YaRN or ALiBi

New

  • 584 downloads
  • 224 likes
  • 110 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install long-context-rope-yarn-extension

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent helps you choose a positional encoding method, RoPE, YaRN or ALiBi, apply it to a pretrained model to handle long documents, then fine-tune if needed. It covers interpolation and extrapolation strategies.

Mostly picked by

Updated November 2, 2026

Card for the “Extending the context window of a Transformer” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: installation, RoPE and ALiBi setup in attention
  • references/rope.md, extension_methods.md and fine_tuning.md: RoPE, extension methods and fine-tuning

Good fit for

  • You want to process documents of 32,000 tokens or more
  • You extend a pretrained model beyond its context limit

Not for

    Tags

    • long context
    • rope
    • yarn
    • transformers

    About

    You say

    “Extend my model's context window to 128k tokens with YaRN for long contracts.”

    Card for the “Extending the context window of a Transformer” skill

    Skill published by Orchestra Research under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to extend a model's context window with RoPE, YaRN or ALiBi
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/extension_methods.md14.7 KB
    • references/fine_tuning.md16.6 KB
    • references/rope.md12.2 KB
    • SKILL.md15.7 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/19-emerging-techniques/long-context
    Licence
    MIT

    Notice

    « long-context » (Orchestra Research, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.