Model Reference 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.

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.