FC

i4never

AI & ML interests

None yet

Recent Activity

Organizations

Tiger Research's profile picture

i4never's activity

reacted to BlinkDL's post with 🔥 29 days ago
view post
Post
3963
RWKV-6-world-v3 (+3.1T tokens) is our best multilingual 7B model as of now: 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 :)
upvoted an article 6 months ago
view article
Article

The Technology Behind BLOOM Training

• 21