optimum-neuron/pr_1109/en/training_tutorials/finetune_llms_overview.md

🚀 Tutorials: How To Fine-tune & Run LLMs

Learn how to run and fine-tune models for optimal performance with AWS Trainium.

<h3 style="margin: 0 0 8px 0 !important; font-size: 18px !important;

font-weight: 600 !important; color: #24292e !important;"> Llama 3.1

<p style="margin: 0 !important;

font-size: 14px !important; color: #586069 !important; line-height: 1.4 !important;"> Instruction Fine-tuning of Llama 3.1 8B with LoRA on the Dolly dataset

<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/optimum/neuron/training_tutorials/qwen3-logo.png" alt="Qwen3" style="width: 100% !important;

height: 100% !important; object-fit: cover !important; border: none !important; border-radius: 8px 8px 0 0 !important;" onerror="this.outerHTML='🔷'"/>

<h3 style="margin: 0 0 8px 0 !important; font-size: 18px !important;

font-weight: 600 !important; color: #24292e !important;"> Qwen3

<p style="margin: 0 !important;

font-size: 14px !important; color: #586069 !important; line-height: 1.4 !important;"> Fine-tune Qwen3 8B with LoRA on the Simple Recipes dataset

<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/optimum/neuron/training_tutorials/sagemaker-logo.png" alt="SageMaker Hyperpod" style="width: 100% !important;

height: 100% !important; object-fit: cover !important; border: none !important; border-radius: 8px 8px 0 0 !important;" onerror="this.outerHTML='☁️SageMaker'"/>

<h3 style="margin: 0 0 8px 0 !important; font-size: 18px !important;

font-weight: 600 !important; color: #24292e !important;"> Llama 3.2 on SageMaker

<p style="margin: 0 !important;

font-size: 14px !important; color: #586069 !important; line-height: 1.4 !important;"> Continuous Pretraining of Llama 3.2 1B on SageMaker Hyperpod

What you'll learn

These tutorials will guide you through the complete process of fine-tuning large language models on AWS Trainium:

• 📊 Data Preparation: Load and preprocess datasets for supervised fine-tuning
• 🔧 Model Configuration: Set up LoRA adapters and distributed training parameters
• ⚡ Training Optimization: Leverage tensor parallelism, gradient checkpointing, and mixed precision
• 💾 Checkpoint Management: Consolidate and merge model checkpoints for deployment
• 🚀 Model Deployment: Export and test your fine-tuned models for inference

Choose the tutorial that best fits your use case and start fine-tuning your LLMs on AWS Trainium today!