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.
我按照官网尝试, 应该是只训练time_state,然而报错
RuntimeError: element o of tensors does not require grad and does not have a grad_fn