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.

Using the RWKV architecture with linear time v1.0.0

Use this resource to run a hybrid RNN-Transformer in linear time without a KV cache

New

  • 349 downloads
  • 154 likes
  • 197 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install rwkv-linear-time-architecture

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 guides you through installing RWKV, loading a model and using it in parallel mode for training or sequential mode for inference. It explains the differences from a Transformer and how model state is managed.

Mostly picked by

Updated November 2, 2026

Card for the “Using the RWKV architecture with linear time” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: installation, loading and generation in GPT and RNN modes
  • references/architecture-details.md, rwkv7.md and state-management.md: architecture, version 7 and state management

Good fit for

  • You want long context without a growing KV cache
  • You test an architecture alternative to Transformers

Not for

    Tags

    • architecture
    • rnn
    • transformer
    • inference

    About

    You say

    “Load an RWKV model and generate text token by token in RNN mode.”

    Card for the “Using the RWKV architecture with linear time” 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 run a hybrid RNN-Transformer in linear time without a KV cache
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/architecture-details.md9.4 KB
    • references/rwkv7.md10.6 KB
    • references/state-management.md9.6 KB
    • SKILL.md7.2 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/01-model-architecture/rwkv
    Licence
    MIT

    Notice

    « rwkv-architecture » (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.