I get the following error trying to save a quantized model. Can anyone help? Thanks. quantize model quantized_model = torch.quantization.quantize_dynamic( model, {torch.nn.Linear}, dtype=torch.qint8 ) quantized_model.save_pretrained(quantized_dir) AttributeError Tra…

I found the solution here [image] Pegasus Model Weights Compression/Pruning Models @lewtun I chose dynamic quantization approach. And I dont think from_pretrained support loading quantised models. I’d be happy if you can take a look. Can we hop on a google meet call and y…

Error saving quantized model

Intermediate

rohanj November 24, 2022, 9:59am 3

How did this issue got resolved? Am still getting the same error.

Topic		Replies	Views
Model quantization Models	5	2622	February 15, 2023
Problem with pushing quantized model to hub 🤗Transformers	3	305	October 14, 2024
ValueError: The model is quantized with QuantizationMethod.QUANTO and is not serializable 🤗Transformers	1	333	May 20, 2024
Issues when trying to save quantized model locally Beginners	0	344	May 21, 2024
Exception in save_pretrained due to recent changes 🤗Transformers	0	178	June 23, 2024

Error saving quantized model

Related topics