🇮🇹 Artemide (/arˈtɛmide/) 3.5
This model is a finetuned version of Phi-3.5-mini-instruct on the ReDiX/DataForge dataset. The dataset is a mixture of high quality italian and english multiturn conversations.
🏆 Evaluation (OPEN ITA LLM Leaderboard)
| Model | Parameters | Average | MMLU_IT | ARC_IT | HELLASWAG_IT |
|---|---|---|---|---|---|
| ReDiX/Artemide-3.5 | 3.82 B | 57.87 | 60.16 | 52.1 | 61.36 |
| meta-llama/Meta-Llama-3.1-8B-Instruct | 8.03 B | 56.97 | 58.43 | 48.42 | 64.07 |
| microsoft/Phi-3.5-mini-instruct | 3.82 B | 56.82 | 60.03 | 49.19 | 61.25 |