DeepMount00/Qwen2-1.5B-Ita
DeepMount00/Qwen2-1.5B-Ita is a 1.5 billion parameter Qwen2-based language model specifically fine-tuned for the Italian language, featuring a 131072 token context length. This compact model demonstrates performance comparable to the 9 billion parameter ITALIA model by iGenius, particularly excelling in multitask language understanding (MMLU). It is optimized for efficient and effective Italian language applications, offering a balance between size and capability.
No reviews yet. Be the first to review!