thrfirs / rwkv-lm-lora Goto Github PK
View Code? Open in Web Editor NEWThis project forked from blealtan/rwkv-lm-lora
RWKV is a 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.
License: Apache License 2.0