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.
- Recommended by
- 3
- GitHub stars
- 15k
- Licence
- Apache-2.0
- Language
- Python
- Last commit
- 31 Oct 2026
What people said
“You can see all the development directly from them: Last week version 7 was released and every time they make significant improvements.”
“I think could be used, but not all versions (namely instruction fine-tuned models trained on alpaca data)”
“RWKV RNN: Better than ChatGPT? (328 points)”
Not software, abandoned or listed by mistake? Report this listing