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.
Target： For me, I am new to huggingface, just want to convert my fine-tuned model(pth) into huggingface, which can be directly downloaded and used.
Done:
113
I've seen this issue, tried it, but it didn't work. I also left a comment.