from trl import SFTTrainer
 
max_seq_length = 3072 # max sequence length for model and packing of the dataset
 
trainer = SFTTrainer(
    model=model,
    args=args,
    train_dataset=dataset,
    peft_config=peft_config,
    max_seq_length=max_seq_length,
    tokenizer=tokenizer,
    packing=True,
    dataset_kwargs={
        "add_special_tokens": False,  # We template with special tokens
        "append_concat_token": False, # No need to add additional separator token
    }
)