Sean McLeish @SeanMcleish · 11 Nov 2025
We see our biggest gains on GSM8K, removing >25% of parameters from TinyLlama, and looping a core block beats finetuning the fixed depth baseline on a per FLOP basis. 4/7 https://t.co/2k2cvSQwrS
1 820Views
31Likes
0Reposts
1Replies
0Quotes
3Bookmarks
Is that a lot?
0.48×vs under 10K median3 808 views is typical
2.8× audienceReachviews ÷ followers
1.76%Engagement rateof viewers reacted