# Italian language optimization

FastwebMIIA is a 7-billion-parameter Italian artificial intelligence model developed by Fastweb, designed specifically for Italian and English, and supports long document processing.

This is a sentence transformer model based on Italian-ModernBERT-base, specifically designed for calculating sentence similarity and feature extraction.

Velvet-2B is a 2-billion-parameter Italian-English bilingual large language model, trained from scratch based on the Transformer architecture, focusing on text generation and comprehension tasks.

A fine-tuned version based on VAGOsolutions/SauerkrautLM-gemma-2-9b-it, optimized for Italian language performance with support for 8k context length.

Minerva is an Italian-English bilingual large language model developed by Sapienza NLP, based on the Mistral architecture with 7 billion parameters, supporting instruction-following and dialogue tasks.

A version fine-tuned from Microsoft/Phi-3.5-mini-instruct, optimized for Italian language performance—a small yet powerful language model

Italian language-optimized large language model based on Meta-Llama-3.1-8B-Instruct

Italia 9B is an open-source large language model developed by iGenius, specifically designed for the Italian language. It understands the linguistic and cultural nuances of Italian and also performs excellently in English and translation tasks.

Qwen2 1.5B is a compact language model specifically optimized for Italian, with performance close to ITALIA (iGenius) but 6 times smaller in size.

An Italian large language model optimized based on Meta-Llama-3-8B, supporting English and Italian text generation tasks

Minerva-1B-base-v1.0 is a 1-billion-parameter Italian-English bilingual large language model jointly developed by Sapienza NLP with FAIR and CINECA, trained on 200 billion tokens (100 billion each for Italian/English)