I have cloned the code for GenerationMixin
from transformers/src/transformers/generation_utils.py
and have modified it.
I have the following model and tokenizer.
tokenizer = AutoTokenizer.from_pretrained('t5-small')
model = T5ForConditionalGeneration.from_pretrained('t5-small').cuda().eval()
Now, while calling model.generate
, how do I ensure that .generate()
in my modified GenerationMixin
is used?