Quantization made by Richard Erkhov.
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.
This qwen2 model was trained 2x faster with
Unsloth and Huggingface's TRL library.
