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, and free sentence embedding.
Apache License 2.0
11.99k
stars
825
forks
source link
[RWKV-v5] use register_buffer instead of frozen params #213
also fixed a bug due to this in
MishGLU