Hi all, Used this code to export mentioned model to ONNX format: import torch from transformers import MBartForConditionalGeneration, MBart50TokenizerFast model_path = "./mbart_large_50_model" model = MBartForConditionalGeneration.from_pretrained(model_path) tokenizer = MBart50TokenizerFast.from_…

Using ONNX format of the facebook/mbart-large-50-many-to-many-mmt?

John6666 June 23, 2025, 12:11am 3

It is recommended to use Optimum as much as possible when converting to ONNX format.

Topic		Replies	Views
How to export facebook/mbart-large-50-many-to-many-mmt to ONNX format? Beginners	3	34	December 17, 2024
How to export facebook/mbart-large-50-many-to-many-mmt to TorchScript format? Beginners	8	48	December 17, 2024
How do we quantize facebook / mbart-large-50-one-to-many-mmt to ONNX runtime 🤗Transformers	2	804	June 10, 2021
Export M2M100 model to ONNX 🤗Transformers	13	3496	June 15, 2023
MBART-50 looks not compatible with pipeline 🤗Transformers	0	68	July 10, 2024