Generazione di testo con RLHF

In questo esercizio lavorerai con un modello pre-addestrato con RLHF chiamato lvwerra/gpt2-imdb-pos-v2. È l’occasione per ripassare come costruire una pipeline di Hugging Face e usarla per testare un caso d’uso dei modelli addestrati con RLHF: generare recensioni di film.

Gli oggetti pipeline, AutoModelForCausalLM, and AutoTokenizer sono già stati importati da transformers. Il tokenizer è già stato caricato

Questo esercizio fa parte del corso

Reinforcement Learning from Human Feedback (RLHF)

Visualizza il corso

Istruzioni dell'esercizio

Imposta il nome del modello su lvwerra/gpt2-imdb-pos-v2, il modello pre-addestrato con RLHF.
Usa la funzione pipeline per creare una pipeline di text-generation.
Usa la pipeline di generazione del testo per generare una continuazione della recensione fornita.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

# Set the model name
model_name = ____
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Create a text generation pipeline
text_generator = pipeline(____, model=model, tokenizer=tokenizer)

review_prompt = "Surprisingly, the film"

# Generate a continuation of the review
generated_text = text_generator(____, max_length=10)
print(f"Generated Review Continuation: {generated_text[0]['generated_text']}")

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Reinforcement Learning from Human Feedback (RLHF)

AvançadoNível de habilidade

4.8+

Inizia il corso gratis

This chapter introduces the basics of Reinforcement Learning with Human Feedback (RLHF), a technique that uses human input to help AI models learn more effectively. Get started with RLHF by understanding how it differs from traditional reinforcement learning and why human feedback can enhance AI performance in various domains.

Exercise 1: Introduzione a RLHF Exercise 2: Generazione di testo con RLHF

Esercizio in corso

Exercise 3: Classificare il testo generato per RLHF Exercise 4: RL vs. RLHF Exercise 5: Esplorare gli LLM pre-addestrati Exercise 6: Tokenizza un insieme di dati testuale Exercise 7: Fine-tuning per la classificazione delle recensioni Exercise 8: Preparare i dati per RLHF Exercise 9: Preparare l'insieme di dati delle preferenze Exercise 10: Estrazione dei prompt

Discover how to set up systems for gathering human feedback in this Chapter. Learn best practices for collecting high-quality data, from pairwise comparisons to uncertainty sampling, and explore strategies for enhancing your data collection.

Exercise 1: Methods for high-quality feedback gathering Exercise 2: Understanding comparison and rating in RLHF Exercise 3: Comparing slogans for a gym campaign Exercise 4: Measuring feedback quality and relevance Exercise 5: Low confidence Exercise 6: K-means for feedback clustering Exercise 7: Active learning Exercise 8: Implementing an active learning pipeline Exercise 9: Active learning loop

In this Chapter, you'll get into the core of Reinforcement Learning from Human Feedback training. This includes exploring fine-tuning with PPO, techniques to train efficiently, and handling potential divergences from your metrics' objectives.

Exercise 1: Reward models explored Exercise 2: Initializing the reward Exercise 3: Setting up the reward trainer Exercise 4: Training with PPO Exercise 5: Initialize the PPO trainer Exercise 6: PPO fine-tuning Exercise 7: Efficient fine-tuning in RLHF Exercise 8: Prepare for 8-bit Training Exercise 9: Train with LoRA

Explore key techniques for assessing and improving model performance in this last Chapter of Reinforcement Learning from Human Feedback (RLHF): from fine-tuning metrics to incorporating diverse feedback sources, you'll be provided with a comprehensive toolkit to refine your models effectively.

Exercise 1: Model metrics and adjustments Exercise 2: Mitigating negative KL divergence Exercise 3: Checking the reward model Exercise 4: Incorporating diverse feedback sources Exercise 5: Majority voting on multiple data sources Exercise 6: Unreliable data source identification Exercise 7: Evaluating RLHF models Exercise 8: Interpreting curves Exercise 9: Evaluating RLHF with metrics Exercise 10: Wrapping up your RLHF journey