Nie-Yingying

Results 2 comments of Nie-Yingying

> this will load the model with half its memory and should solve your problem. I'll integrate this soon sorry to tell you and it's still oom ![image](https://github.com/Unbabel/COMET/assets/65881015/d062b7f5-617a-433f-942f-105edb0e736c)

I don't change the chat template after I choose model family deepseek-r1-distill-qwen.