ValueError: The input provided to the model are wrong. The number of image tokens is 0 while the number of image given to the model is 1. This prevents correct indexing and breaks batch generation.

[zhangchunjie1999]

This problem occurred when I was running a demo of the 34b model. How can I fix this ？

![Uploading 截屏2024-05-11 11.17.01.png…]()

[zhangchunjie1999]

[KaiyueSun98]

same problem

[zhangchunjie1999]

I found a solution.
In tasks/eval/model_util.py, remove ` # try:

processor = PllavaProcessor.from_pretrained(repo_id)

# except Exception as e:
#     processor = PllavaProcessor.from_pretrained('llava-hf/llava-1.5-7b-hf')`

and add: processor = PllavaProcessor.from_pretrained(repo_id) then: Install the required packages

[MVPavan]

Its image_token_index problem, looks like new LlamaTokenizer image_token_index = 64000 where as pllava config image_token_index = 64002, change it to 64000.

[mztknhao1]

I solved the problem, downgrad the tokenizers version

[zhangchunjie1999]

收到邮件了~   祝安！

[bozagina]

same problem

[zhangchunjie1999]

收到邮件了~   祝安！