view post Post 4693 RWKV-6-world-v3 (+3.1T tokens) is our best multilingual 7B model as of now: BlinkDL/rwkv-6-worldIt's 100% RNN and attention-free. MMLU 54.2% (previous world-v2.1 = 47.9%. note: without eval-boosting tricks such as annealing). RWKV-7-world-v4 soon :) π₯ 16 16 + Reply