# Traditional Chinese Optimization

This is a Tinyllama model specifically optimized for Traditional Chinese through continued pretraining, based on the TinyLlama-1.1B architecture with a pretraining dataset of approximately 2 billion tokens.

An advanced language model optimized for Traditional Chinese, deeply focusing on the linguistic and cultural context of Taiwan, excelling in language understanding and generation tasks

TAIDE-LX-7B-Chat is a Traditional Chinese dialogue model developed based on LLaMA2-7B, optimized for Taiwanese linguistic and cultural characteristics, with enhanced office tasks and multi-turn dialogue capabilities

Breeze-7B is a family of language models based on Mistral-7B, specifically designed for Traditional Chinese, offering base models and instruction-tuned versions.

A large language model based on LLaMa2-13b, supporting Traditional Chinese, in GGUF format

A Taiwanese LLM model based on LLaMa2-7b, further pre-trained on 20 billion Traditional Chinese tokens and fine-tuned with millions of dialogues

A full-parameter fine-tuned Traditional Chinese model based on LLaMa 2, specifically designed for Taiwanese cultural applications