Set push_to_hub=True in your [TrainingArguments]:

training_args = TrainingArguments(output_dir="my-awesome-model", push_to_hub=True)

Pass your training arguments as usual to [Trainer]:

trainer = Trainer(
     model=model,
     args=training_args,
     train_dataset=small_train_dataset,
     eval_dataset=small_eval_dataset,
     compute_metrics=compute_metrics,
 )

After you fine-tune your model, call [~transformers.Trainer.push_to_hub] on [Trainer] to push the trained model to the Hub.