RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.
Why do you think that https://github.com/lucidrains/token-shift-gpt is a good alternative to RWKV-v2-RNN-Pile
RWKV-v2-RNN trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.
Why do you think that https://github.com/lucidrains/token-shift-gpt is a good alternative to RWKV-v2-RNN-Pile