CommencerCommencer gratuitement

Fine-tuning Llama for customer service QA

You work at a company that builds customer service chatbots. Your team uses the Llama models in your customer service bot, and you want to improve the model by fine-tuning on a question-answering dataset related to customer service. To ensure the best performance out of these models, your team will fine-tune a Llama model for this task using the bitext dataset.

The training script is already almost complete, the only thing missing is the final step where you bring together the model, tokenizer, training dataset, and training arguments and start training.

Cet exercice fait partie du cours

Fine-Tuning with Llama 3

Afficher le cours

Instructions

  • Import the class that lets you conduct supervised fine-tuning from its library.
  • Instantiate the class used for supervised fine-tuning by passing the model, tokenizer, dataset, and training_arguments.
  • Run the instance method to start fine-tuning your model.

Exercice interactif pratique

Essayez cet exercice en complétant cet exemple de code.

# Import the supervised fine-tuning class
from ____ import ____

# Instantiate fine-tuning class
trainer = ____(
  	# Pass necessary arguments
    ____=____,
    ____=____,
    ____=____,
    ____=____,

)

# Start training 
trainer.____()
Modifier et exécuter le code