at://
/
app.bsky.feed.post
/
3lpnp2xyilk2y
sign in
All
4
Record
2
Post
1
PostEmbed
1
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
🧵[2/n] 💡 SFT Updates Are Dense 💡 Unlike RL, Supervised Fine-Tuning (SFT) updates are much denser 🧠 📊 Sparsity is low — at most only 15.31% of parameters remain untouched.
May 21, 2025
Sagnik Mukherjee
