I’ve port facebook/m2m100_418M to ONNX for translation task using this but when visualize by netron, it required 4 inputs: input_ids, attention_mask, decoder_input_ids, decoder_attention_mask and I don’t know how to inference with ONNX-runtime. [image] How can I solve this problem ? Thanks in ad…

Export M2M100 model to ONNX

double May 16, 2022, 4:25pm 2

Did you find a solution?

Topic		Replies	Views
How can I use the ONNX model? 🤗Transformers	2	1742	January 29, 2024
Optimize large scale transformer model inference with ONNX Runtime Models	0	384	January 18, 2022
Transformers.onnx vs optimum.onnxruntime 🤗Optimum	1	1165	September 12, 2022
How do we quantize facebook / mbart-large-50-one-to-many-mmt to ONNX runtime 🤗Transformers	2	810	June 10, 2021
Supporting ONNX optimized models 🤗Transformers	16	3064	September 1, 2021