torch.save fails with pickling error on mct quantized model

[irenaby]

Issue Type

Bug

Source

pip (model-compression-toolkit)

MCT Version

1.10.0

OS Platform and Distribution

Ubuntu 20.04

Python version

3.10

Describe the issue

torch.save fails with pickling error on mct quantized model

Expected behaviour

No response

Code to reproduce the issue

import torch
import torchvision as tv
import model_compression_toolkit as mct

model = tv.models.get_model('alexnet')
model.eval()
def gen():
    yield [torch.rand(1, 3, 224, 224)]
qmodel, qinfo = mct.ptq.pytorch_post_training_quantization_experimental(model, gen)
torch.save(qmodel, '/tmp/qmodel.pt')

Log output

Traceback (most recent call last):
  File "/Vols/vol_design/tools/swat/users/irenab/ml-frameworks-uni-converter/uni/fx_rename/fx_parser/tests/mct_bug.py", line 37, in <module>
    torch.save(qmodel, '/tmp/qmodel.pt')
  File "/data/projects/swat/envs/irenab/py3.10_torch2.0/lib/python3.10/site-packages/torch/serialization.py", line 441, in save
    _save(obj, opened_zipfile, pickle_module, pickle_protocol)
  File "/data/projects/swat/envs/irenab/py3.10_torch2.0/lib/python3.10/site-packages/torch/serialization.py", line 653, in _save
    pickler.dump(obj)
_pickle.PicklingError: Can't pickle <function <lambda> at 0x7fb0557251b0>: attribute lookup <lambda> on model_compression_toolkit.core.pytorch.default_framework_info failed