Paradigm releases Limite 1B -Violetto technical report: a tiny model trained from scratch to max out math per parameter
tensorqt · x · 2026-10-07
Paradigm released the technical report for Limite 1B -Violetto, its first model, trained from scratch with the goal of pushing mathematical capability per parameter to its limits.
A collaborator shared the news, noting the team learned a lot during training. The report is publicly available for anyone interested in how far small models can be pushed on math reasoning.
Related event: Paradigm Open-Sources Limite 1B - Violetto, Its First Math-Focused Model(6 posts)→
More from Research
- Debate over the massive Riemann proof: do simpler proofs exist, or is reality just irreducibly complex? — eigenhector · 2026-11-22
- Benjamin Bratton on the RH proof furor: centaur cognition kills the lone-genius myth — bratton · 2026-11-22
- NAT: streaming action tokenizer closes latency gap with flow action heads, trained on 49k hours — YuXiang_IRVL · 2026-11-22
- RoboDojo sim benchmark audit finds loose joints, ignored material properties — AIFlow_ML · 2026-11-22
- Berliner study: existing user-simulator metrics catch only 5-6 of 10 injected failures — geoffwolfe · 2026-11-22
- LeCun coauthors prove standard world models fail at counterfactuals, fix needs no retraining — alex_verem · 2026-11-22