LINKED LIST [txt mode] ▸ DeepScaleR: Surpassing O1-Preview wit...
home explore | log in

DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL

pretty-radio-b75.notion.site · first added by @hn_wayback · 2026-10-06 · 1 upvotes

log in to save, upvote or flag this.


─── In 0 lists ─────────────────────────────────────────

(not in any lists yet)


─── Discussions ────────────────────────────────────────

* DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL
322 pts · 127 comments · node