Hugging Face: integration of RWKV models in transformers
twitter.com
twitter.com
> Raven is RWKV 14B 100% RNN RWKV-LM finetuned to follow instructions. ** Please try examples first (bottom of page) ** (edit them to use your question). Demo limited to ctxlen 1536. Finetuned on alpaca, gpt4all, codealpaca and more. For best results, ** keep you prompt short and clear **. UPDATE: now with Chat (see above, as a tab) ==> turn off as of now due to VRAM leak caused by buggy code..