Paradigma releases Limite 1B - Violetto, a small open-weight math reasoning model
Source
Paradigma
Author
Paradigma
Date
Key takeaways · AI-distilled
Limite is a dense 1B transformerThe neural network architecture behind modern AI models, built on attention — letting every word directly consider every other word in parallel.Full definition → trained from scratch with a 131k-token context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →. Paradigma credits its sample efficiency to data curation and an architecture drawn from community pretrainingThe first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.Full definition → speedrun competitions.
Post-training mixed synthetic data generation, curated SFT and RL. Paradigma kept instruction tuning deliberately light to test whether a model needs an assistant persona to perform well, so Limite is meant for single-turn answers.
Paradigma lists limitations in instruction following and scope: Limite can lose track of what a prompt asks and reinterpret it as a different, often mathematical, task.
Alongside Apache-2.0 weights, the release includes the evaluations, a value model used during training, and a custom vLLM inference plugin. Paradigma says a technical report is coming soon and that Limite is the first of several models aimed at science and autonomous research.
Terms in this piece · Glossary
reasoning model — A model trained to think — generating extended internal reasoning before answering — trading time and tokens for accuracy on hard problems.
transformer — The neural network architecture behind modern AI models, built on attention — letting every word directly consider every other word in parallel.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
Why it matters
Paradigma's 1B-parameter Limite model reportedly beats a 30B model on BeyondAIME (74.25% vs 70%) using under 300B training tokens, a notable efficiency claim for anyone evaluating small specialist math models.
