hugging facemii-llm discord

MII-LLM an indipendent AI research community

We are specializing ourselves in training, evaluating, developing and deploying AI systems. All our services are supported by Seeweb cloud provider. We ♥ Italy and open source.

Maestrale

Is a 7 billion open source model fine tuned for producing good Italian both semantically and syntatically. Maestrale is able to integrate with tools via json and API calls and has reasoning capabilities. It is one of the best Italian open source models and all anonymized conversations will be published as open source datasets.

Hero image
Image

Italian LLMs leaderboard

The ranking of the open source Italian LLMs on reproducible evaluation benchmarks as mmlu_it, arc_c_it, hellaswag_it and others.

Image

Pinocchio ITA leaderboard

Specialized benchmarks on specific topics as logic, math, law, foreign language and culture for Italian finetuned LLMs

Open source

Open source contributions

We have many thousands of downloads. Here a list of our most important contributions to the ML/AI open source community

lm-evaluation-harness

We contribute to add mmlu and arc_c evaluation benchmark for Italian based tasks. Our bechmarks are now used by many LLMs groups for evaluating Italian based LLMs

Zefiro trilogy

One of the first completely open source Italian model in three versions: continual pre-trained, SFT and DPO

Gazzetta Ufficiale

The entire corpus of the current Italian laws as an open source dataset

Ultrafeedback ITA

Translated version of the ultrafeedback dataset for SFT fine tuning

Ultrafeedback binarized ITA

Translated version eng to ita of the popular ultrafeedback binarized dataset for DPO fine tuning.

Usenet conversations

The biggest dataset of real conversations in the Italian language from usenet

mmlu-pro

We tranlated the mmlu-pro dataset to Italian and contributed to integrate into the lm-eval command for evaluating Italian LLM on difficult tasks

Maestrale series

A series of open source LLMs a fine tuned versions of mistral 7 Billion for producing Italian

Pinocchio Eval dataset

A multimodal and text dataset for evaluating LLMs on Italian tasks

lm-evaluation-harness fork

A fork of lm-evaluation-harness with Italian specific tasks: mmlu arc-c hellaswag pinocchio-law, pinocchio-logic, pinocchio-math and reasoning like mmlu-pro-ita