[Python] What is the difference, if any, between model.half() and...

Example:

# pip install transformers
from transformers import AutoModelForTokenClassification, AutoTokenizer

# Load model
model_path = 'huawei-noah/TinyBERT_General_4L_312D'
model = AutoModelForTokenClassification.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)

# Convert the model to FP16
model.half()


vs.

model.to(dtype=torch.float16)


What is the difference, if any, between model.half() and model.to(dtype=torch.float16) in huggingface-transformers?

Continue reading...