Llava_Qwen2

Llava_Qwen2 copied to clipboard

使用llava1.5的数据进行预训练和微调会出现模型输出不停止的情况[Usage]

3

### Describe the issue 推理时会一直输出直到max_new_token 上限 

AIaimuti

Qwen2 version

7

请问您使用的是base model 还是 instruct model？

King-king424

[Question] Error with 'Qwen2Tokenizer' object has no attribute 'legacy'

3

### Question _No response_

PangziZhang523

[Question] About the performance.

5

### Question I wonder about the performance when using Qwen2 as the LLM. Does it outperform the original LLaVA-v1.5? By the way, are there any scripts for instruction tuning? I...

Haochen-Wang409