# Bilingual

EXAONE-3.0-7.8B-Instruct is a bilingual (English and Korean) pre-trained generative model developed by LG AI Research, featuring 780 million parameters. The model is pretrained on a curated dataset of 8 trillion tokens and has undergone supervised fine-tuning along with direct preference optimization, demonstrating competitively benchmarked performance compared to similar-sized open models.

Llama3.1-70B-Chinese-Chat is an instruction-tuned language model based on the Meta-Llama-3.1-70B-Instruct model, specifically designed for Chinese and English bilingual users, with diverse capabilities such as role-playing and tool utilization. This model is fine-tuned using the ORPO algorithm, significantly reducing instances where Chinese questions receive English answers and cases of mixed language responses, particularly showing notable improvements in role-playing, function invocation, and mathematical abilities.

Huanyuan-DiT is Tencent's first bilingual DiT architecture AI model, focusing on Chinese element understanding. It boasts long-text comprehension capabilities and fine-grained semantic understanding. This model can analyze and understand information in lengthy texts and generate corresponding artistic works, including but not limited to portraits, creative designs, etc. The launch of Huanyuan-DiT is significant in enhancing the depth and breadth of Chinese text understanding and promoting bilingual communication between Chinese and English.

Taiyi-Diffusion-XL is an open-source text-to-image generation model based on the Stable Diffusion framework, supporting both English and Chinese text-to-image generation. It represents a significant advancement over previous Chinese text-to-image models. The model can generate photo-realistic images based on textual descriptions, supports various image styles, and boasts high quality and diversity in generated images. It adopts an innovative training approach, extends vocabulary and position encoding to support long texts and Chinese, and is trained on large-scale bilingual datasets, ensuring its robust English and Chinese generation capabilities.