AI Model / Open-weight model
Open-weight System One model for machine-intuition style judgment tasks, built on a T5Gemma 2 encoder-decoder base. The page shows what the model does, how it is used in Python and via CLI/HTTP API, and includes benchmark and example sections.
The snapshot clearly presents an AI model with a concrete purpose: judging text, structured data, and images and returning probabilities over candidate answers or actions. It includes enough evidence for a useful listing, with quick-start usage, code examples, CLI and HTTP API references, and benchmark-oriented sections.
The page does not fully show the model card details, evaluation results, or license terms in the visible text, so a visitor cannot tell the full performance profile or deployment constraints from the snapshot alone.
Last evaluated 16 days ago. Current rank #995. Down 6 spots in the rankings.
A 150M ModernBERT-based token classification model that extracts verbatim evidence spans for RAG and related pipelines, reducing the need for an LLM call to highlight answers.
JetBrains introduces Mellum2, an open-source 12B model built for software engineering workflows, routing, Q&A, RAG, sub-agents, and private deployment.
An open-source 26M parameter function-calling model designed to run on very small devices, with a local quickstart, Python usage, and a playground for testing and finetuning.
A vision-language foundation model for autonomous driving that combines 3D perception, driving VQA, and motion planning in one framework. The repo shows performance tables, model structure, and links to the paper, blog, and model downloads.
