# ChatML Template

Qwen2-7B is a multilingual role-playing large language model that supports English, Korean, Japanese, Chinese, and Spanish, with a context length of 32k.

TowerInstruct-7B-v0.2 is a multilingual instruction fine-tuned model developed by Unbabel, based on the Llama 2 architecture, supporting translation tasks in 10 languages.

A multilingual large language model fine-tuned based on Microsoft's Orca-2-13b model, supporting English, French, Spanish, Hindi, and Chinese. It has undergone comprehensive fine-tuning on multiple datasets, achieving a test loss of 0.18.