DataBubble·

Model Detail

LateOn

—

Provider: lightonaiCategory: llmPipeline: sentence-similarity

DB Score

17.2

Downloads

Likes

Day

+0.0%

Week

+0.0%

Month

+0.0%

Overview

LateOn is a large language model with 75M parameters released by lightonai. The model is registered under the sentence-similarity pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.

Technical

LateOn ships with 75M parameters. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.

Use Cases

LateOn is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.

Download History

Research Paper

arXiv: 1908.10084→

Model Info

Licenseapache-2.0

Citations20,941 (2503 influential)

Recent newsView all news →

DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search

arXiv:2607.27178v2 Announce Type: replace Abstract: State-of-the-art retrieval models increasingly rely on closed training data, creating a reproducibility gap. We present an open end-to-end recipe for training retrieval models and study how English supervision transfers to multilingual retrieval th

Related Models

LightOnOCR-2-1B

lightonai · 189K downloads

Reason-ModernColBERT

lightonai · 17K downloads

bge-small-en-v1.5

BAAI · 59.9M downloads

paraphrase-multilingual-MiniLM-L12-v2

SBERT · 48.0M downloads