Tutorials for Intel® Gaudi® Technology

Explore how to use retrieval augmented generation (RAG) with the Intel® Gaudi® processor and Hugging Face*.

Use GenAI to create a chatbot for visual question and answering based on images.

Explore dataset that enhances question-and-answering quality.

Access an example of a chatbot that summarizes the content of documents or reports.

This copilot example is designed for code generation in Microsoft Visual Studio* code.

ChatQnA is an example of a chatbot for question-and-answering through RAG.

Chat using your local documentation through LocalGPT* on Intel Gaudi 2 AI accelerators with the Llama 2 model.

Learn how to fine-tune Llama 2 more efficiently in under six minutes.

Use the profiler tool and TensorBoard* plug-in with Intel Gaudi software to modify any model for better performance.

Find dynamic data and operations in your models and explore ways to reduce them for better performance.

Run inference on Intel Gaudi architecture using HPU Graph for better performance.

This tutorial provides example training scripts to demonstrate different DeepSpeed* optimization technologies on HPU.

Set up an Amazon EC2* DL1 instance and start training a PyTorch* model on Intel Gaudi architecture.

This tutorial adapts existing Transformer training code and accelerates it using a DistilBERT model. 

Set up an Intel Gaudi processor on Amazon Web Services* and fine-tune a BERT model.

Learn how to take Hugging Face datasets using the PyTorch LightningDataModule to perform text classification on any dataset. 

Get an introduction to PyTorch Lightning using Intel Gaudi AI processors.

Get an overview of mixed precision, which uses both 16-bit and 32-bit floating-point types in a model during training to make it faster and use less memory.

Explore an adaptation of a tutorial for training a classifier using Intel Gaudi AI processors. 

This tutorial demonstrates how to migrate an existing PyTorch workload to the Intel Gaudi platform using a PyTorch plug-in library.