PropagandaPropaganda is a framework designed to evaluate and train LLMs (Large Language Models) on political opinions and bias. We aim to analyze…Mar 16Mar 16
Italian fork of llm-evaluation-harnessWe are excited to announce the release of our fork of the lm-evaluation-harness project, specialized in Italian language tasks. This…Sep 29, 2024Sep 29, 2024
MMLU-PRO-ITA a new eval for Italian LLMsIn a previous post, we as mii-llm lab, described an analysis on evaluating Italian LLMs on different common used benchmarks and launched…Jul 21, 2024Jul 21, 2024
Analysis on Italian LLMs models evaluations.I and Samuele Colombo are the maintainer of the Italian Leaderboard and I have contribute to lm-evaluation-harness adding different…Apr 1, 2024Apr 1, 2024
The trilogy of ZefiroThe trilogy of Zefiro is a set of three open sourced #llms suited for speaking the Italian Language made by following the Zephyr recipes…Feb 21, 2024Feb 21, 2024
Evaluating Italian LLMsWe just released an updated version of the Italian leaderboard created and maintained by Samuele Colombo who continued the work of Federico…Feb 3, 2024Feb 3, 2024
Zefiro an LLM and datasets for the Italian LanguageIn European tradition, a zephyr is a light wind or a west wind, named after Zephyrus, the Greek god or personification of the west wind.Jan 13, 2024Jan 13, 2024
Published innteractCreating a platform for querying open datasets with PDND & nteractPDND (Piattaforma Digitale Nazionale Dati ex Daf) is the Italian big data platform developed by Digital Trasformation Team, the Italian…May 30, 2019May 30, 2019
