RWKV-LM (Agent Skills)

GitHub

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.

No Explicit Rule Files Found

This repository does not currently contain dedicated AI agent rule files (.cursorrules, CLAUDE.md, AGENTS.md).

Read Full Technical Documentation