Allow creating compressor when trust_remote_code=True

[dbogunowicz]

This code:

from compressed_tensors import ModelCompressor
compressor = ModelCompressor.from_pretrained("microsoft/Phi-3-mini-128k-instruct",trust_remote_code=True)

Failed before:

Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "/root/compressed-tensors/.venv/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 983, in from_pretrained
    return config_class.from_dict(config_dict, **unused_kwargs)
  File "/root/compressed-tensors/.venv/lib/python3.10/site-packages/transformers/configuration_utils.py", line 772, in from_dict
    config = cls(**config_dict)
  File "/root/compressed-tensors/.venv/lib/python3.10/site-packages/transformers/models/phi3/configuration_phi3.py", line 158, in __init__
    self._rope_scaling_validation()
  File "/root/compressed-tensors/.venv/lib/python3.10/site-packages/transformers/models/phi3/configuration_phi3.py", line 185, in _rope_scaling_validation
    raise ValueError(f"`rope_scaling`'s type field must be one of ['su', 'yarn'], got {rope_scaling_type}")
ValueError: `rope_scaling`'s type field must be one of ['su', 'yarn'], got longrope

After the diff, we can properly initialize the config (and thus the compressor, although in this example it will be None) with trust_remote_code=True

[rahul-tuli]

nit: Add kwargs in docstring?

[anmarques]

I tested w/ microsoft/Phi-3-mini-128k-instruct both original and after SparseML quantization and it worked