Update checkpoint for transformers>=4.29

#1
by ArthurZ HF staff - opened
Language Technology Research Group at the University of Helsinki org

Automatically merging the PR.

ArthurZ changed pull request status to merged
Language Technology Research Group at the University of Helsinki org

Following the merge of a PR in transformers it appeared that this model was not properly converted. This PR will fix the inference and was tested using the following script:

>>> from transformers import AutoTokenizer, MarianMTModel
>>> tokenizer = AutoTokenizer.from_pretrained('Helsinki-NLP/opus-mt-tc-big-zle-itc')
>>> inputs = tokenizer("' >>en<< Hey how are you?'", return_tensors="pt", padding=True)
>>> model = MarianMTModel.from_pretrained('Helsinki-NLP/opus-mt-tc-big-zle-itc')
>>> print(tokenizer.batch_decode(model.generate(**inputs)))
["<pad> 'Hey how are you?'</s>"]

Sign up or log in to comment