Some weights of Qwen2ForTokenClassification were not initialized from the model checkpoint at /mnt/usercache/huggingface/Qwen2.5-3B-Instruct and are newly initialized: ['score.bias', 'score.weight']

[MJinXiang]

Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.50it/s]
Loading checkpoint shards: 100%|██████████| 2/2 [00:01<00:00, 1.45it/s]�[32m [repeated 5x across cluster]�[0m
Some weights of Qwen2ForTokenClassification were not initialized from the model checkpoint at /mnt/usercache/huggingface/Qwen2.5-3B-Instruct and are newly initialized: ['score.bias', 'score.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

I have met this problem，how can I sovle this problem？