jhyxwd's picture

jhyxwd

jhyxwd

AI & ML interests

None yet

Recent Activity

replied to BlinkDL's post 14 days ago

RWKV-6-world-v3 (+3.1T tokens) is our best multilingual 7B model as of now: https://huggingface.co/BlinkDL/rwkv-6-world It'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 :)

View all activity

Organizations

None yet

models

None public yet

datasets

None public yet