Prepare for 8-bit Training

You wanted to begin RLHF fine-tuning, but you kept running into out-of-memory errors. To address this, you decided to switch to 8-bit precision, which allows for more efficient fine-tuning, by leveraging the Hugging Face peft library.

The following have been pre-imported:

AutoModelForCausalLM from transformers
prepare_model_for_int8_training from peft
AutoModelForCausalLMWithValueHead from trl

This exercise is part of the course

Reinforcement Learning from Human Feedback (RLHF)

Exercise instructions

Load the pre-trained model and make sure to include the parameter for 8-bit precision.
Use the prepare_model_for_int8_training function to make the model ready for LoRA-based fine-tuning.
Load the model with a value head for PPO training.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

model_name = "gpt2"  

# Load the model in 8-bit precision
pretrained_model = AutoModelForCausalLM.from_pretrained(
                                                       model_name, 
                                                       ____=True
                                                      )

# Prepare the model for fine-tuning
pretrained_model_8bit = ____(pretrained_model)

# Load the model with a value head
model = ____.from_pretrained(pretrained_model_8bit)

Edit and Run Code

This exercise is part of the course

Reinforcement Learning from Human Feedback (RLHF)

AdvancedSkill Level

4.8+

Start Course for Free

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: Introduction to RLHF Exercise 2: Text generation with RLHF Exercise 3: Classifying generated text for RLHF Exercise 4: RL vs. RLHF Exercise 5: Exploring pre-trained LLMs Exercise 6: Tokenize a text dataset Exercise 7: Fine-tuning for review classification Exercise 8: Preparing data for RLHF Exercise 9: Preparing the preference dataset Exercise 10: Extracting prompts

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

Current Exercise

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