Update checkpoint for transformers>=4.29

#4
by ArthurZ HF staff - opened
Language Technology Research Group at the University of Helsinki org
edited Oct 10, 2023

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-tr-en')
>>> inputs = tokenizer("Hey!Birlikte öğrenelim", return_tensors="pt", padding=True)
>>> model = MarianMTModel.from_pretrained('Helsinki-NLP/opus-mt-tc-big-tr-en')
>>> print(tokenizer.batch_decode(model.generate(**inputs)))
["<pad> Hey! Let's learn together</s>"]
ArthurZ changed pull request status to merged

Sign up or log in to comment