Parzival - ∞/89 @whyarethis · 07 Apr 2026
As promised. Our first paper and contribution to the amazing work going on to make open source models smaller, faster, and more accessible. So what is it, and why is it important? We discovered what appears to be a universal formula that identifies dead attention heads in any
35 432Views
272Likes
51Reposts
30Replies
13Quotes
230Bookmarks
Is that a lot?
13.4×vs this author's median2 644 views is typical
82Percentile for this authorof 11 recent posts
26.7×vs 10K–100K median1 328 views is typical
163.00%Reachviews ÷ followers
1.03%Engagement rateof viewers reacted