--- language: - en - zh - fr - es - de - pt - ru - it - ja - ko - vi - ar tags: - pytorch - text-generation - causal-lm - rwkv license: apache-2.0 datasets: - cerebras/SlimPajama-627B - EleutherAI/pile --- # RWKV-5 World (Training in Progress) Use rwkv pip package 0.8.14+ for RWKV-5 inference. GUI: https://github.com/josStorer/RWKV-Runner (see Releases) How it works: https://twitter.com/BlinkDL_AI/status/1685230712247795713 ## Model Description RWKV-5 trained on 100+ world languages (70% English, 15% multilang, 15% code). World = Some_Pile + Some_SlimPajama + Some_OSCAR + All_Wikipedia + All_ChatGPT_Data_I_can_find RWKV-5 training: set --my_testing "2r4" in latest RWKV-LM World v1 = 0.59T tokens World v2 = 1.12T tokens Imagine what happens when we use more data :)