Italian fine-tuning focus
According to the model card, the model is specifically fine-tuned for the Italian language across various language tasks.
Open Source Model Profile · DeepMount00
Qwen2-1.5B-Ita is a 1.54B-parameter Qwen2-family text-generation model from DeepMount00. According to the model card, it is fine-tuned for Italian with a documented Transformers usage example.
Qwen2-1.5B-Ita is published by DeepMount00 as a Qwen2 text-generation model for Italian. The captured configuration identifies Qwen2ForCausalLM and Safetensors metadata reports 1,543,714,304 parameters. According to the model card, fine-tuning focused on Italian language tasks and the publisher compares it with the 9B ITALIA model by iGenius.
According to the model card, the model is specifically fine-tuned for the Italian language across various language tasks.
According to the model card, the model averages 46.12 against ITALIA at 43.5, with MMLU 52.16, ARC 36.06, and HELLASWAG 50.15 in the reported table.
According to the model card, loading uses AutoTokenizer and AutoModelForCausalLM with apply_chat_template and a 1024 max-new-tokens example.
Source: DeepMount00/Qwen2-1.5B-Ita
Captured: Unknown. Processed: 2026-09-07T19:34:30.062422+00:00.
Qwen2 1.5B: Almost the Same Performance as ITALIA (iGenius) but 6 Times Smaller 🚀 Model Overview Model Name: Qwen2 1.5B Fine-tuned for Italian Language Version: 1.5b Model Type: Language Model Parameter Count: 1.5 billion Language: Italian Comparable Model: ITALIA by iGenius (9 billion parameters) Model Description Qwen2 1.5B is a compact language model specifically fine-tuned for the Italian language. Despite its relatively small size of 1.5 billion parameters, Qwen2 1.5B demonstrates strong performance, nearly matching the capabilities of larger models, such as the 9 billion parameter ITALIA model by iGenius . The fine-tuning pro…
F001F002F003F004F005F006F007F008F009F010F011F012F013F014F015