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
12.32k
stars
838
forks
source link
How to construct dataset for multi-round dialogue? any examples? #106
Can anyone give some data examples for multi-round dialogue. MOSS and ChatGLM have clear examples, but I can not find examples in RWKV