How can I run the pipeline without the Image input?
#17
by
prakhaaaas
- opened
When I am setting the pipeline to only text-generation instead of image-text-to-text it giving me error.
from transformers import pipeline
import torch
pipe = pipeline(
"text-generation",
model=r"Gemma_3_4B_it\Model",
torch_dtype=torch.bfloat16
)
AttributeError: 'Gemma3Config' object has no attribute 'vocab_size'
Is there any other way to do it?
Am i doing something wrong?