This model has been fine-tuned with the continuous pretraining mode of Unsloth on the gsarti/clean_mc4_it dataset (only 100k rows) to improve the Italian language. The second fine-tuning was performed on the instructed dataset FreedomIntelligence/alpaca-gpt4-italian.

For a detailed comparison of model performance, check out the Leaderboard for Italian Language Models.

Here's a breakdown of the performance metrics:

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.