How to reset parameters from AutoModelFor SequenceClassification?

🤗Transformers
1

Currently to reinitialize a model for AutoModelForSequenceClassification, we can do this:

from transformers import AutoModel, AutoConfig, AutoModelForSequenceClassification

m = "moussaKam/frugalscore_tiny_bert-base_bert-score"
config = AutoConfig.from_pretrained(m)
model_from_scratch = AutoModel(config)

model_from_scratch.save_pretrained("frugalscore_tiny_bert-from_scratch")

model = AutoModelForSequenceClassification(
  "frugalscore_tiny_bert-from_scratch", local_files_only=True
)

Is there some way to just do something like this?

model = AutoModelForSequenceClassification(
  "moussaKam/frugalscore_tiny_bert-base_bert-score", 
  local_files_only=True
  reinitialize_weights=True
)

or something like:

model = AutoModelForSequenceClassification(
  "moussaKam/frugalscore_tiny_bert-base_bert-score", 
  local_files_only=True
)

model.reinitialize_parameters()
2

Also asked on machine learning - How to reset parameters from AutoModelForSequenceClassification? - Stack Overflow