Skip to content

GitLab

Explore

Sign in

R

RWKV LM

Project information

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len

600 Commits
3 Branches
0 Tags

README
Apache License 2.0

Created on

March 27, 2024

Copy SSH clone URLgit@gitlab.wolfspyre.io:mirrored_repos/machinelearning/SmerkyG/RWKV-LM.git
Copy HTTPS clone URLhttps://gitlab.wolfspyre.io/mirrored_repos/machinelearning/SmerkyG/RWKV-LM.git

Loading

🐾❤️ Strive to be the person your dogs believe you are ❤️🐾