lianghsun/Llama-3.2-Taiwan-3B-Instruct

The lianghsun/Llama-3.2-Taiwan-3B-Instruct is a 3.2 billion parameter instruction-tuned causal language model developed by Huang Liang Hsun. Based on the Llama-3.2-Taiwan-3B foundation model, it is fine-tuned with extensive Traditional Chinese conversational datasets from Taiwan and multilingual datasets. This model is specifically designed to generate dialogues with knowledge and style relevant to Taiwan, making it suitable for applications requiring localized Traditional Chinese interaction.