Marin 535B-A23B open model training crosses halfway, Percy Liang shares learnings
ericjang11 · x · 2026-10-07
- Stanford's Percy Liang announced that Marin's 535B-parameter (23B active, MoE) open model training has passed the halfway mark.
- The team published observations and learnings from the run so far, a useful reference for large-scale open-model training.
More from Models
- Models rapidly improve at predicting experiment outcomes, may close 90% of gap by 2030 — SaxenaNayan · 2026-10-07
- Reflection Beam and Mistral Large 4 hit GLM-5.2 level, sparking distillation gap debate — Yuchenj_UW · 2026-10-07
- Mistral's new 1T-param/49B-active model beats rivals on legal benchmarks — BLUECOW009 · 2026-10-07
- Mistral CEO: Large 4 trained on our own compute, 'RL shows no sign of saturation' — sivareddyg · 2026-10-07
- Decider model gains from unmasking and more data, authors deny benchmaxxing — antoine_chaffin · 2026-10-07
- Tesla's Grok voice goes hoarse but can't hear itself — a look at AI engineering shortcuts — PTrubey · 2026-10-07