optimum-neuron/main/en/inference_tutorials/notebooks.md

# Notebooks

We prepared some notebooks for you, so that you can run directly tutorials in the documentation.

| Notebook                                                                                                                                                                                | Description                                                                                                                                                                       |        Studio Lab                                                                                                                                                                                                       |
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| [Create your own chatbot with llama-2-13B on AWS Inferentia](https://github.com/huggingface/optimum-neuron/blob/main/notebooks/text-generation/llama2-13b-chatbot.ipynb)                | Show how to run LLama-2 13B chat model on AWS inferentia 2.                                                                                                                       | [![Open in AWS Studio](https://studiolab.sagemaker.aws/studiolab.svg)](https://studiolab.sagemaker.aws/import/github/huggingface/optimum-neuron/blob/main/notebooks/text-generation/llama2-13b-chatbot.ipynb)           |
| [How to generate images with Stable Diffusion](https://github.com/huggingface/optimum-neuron/blob/main/notebooks/stable-diffusion/stable-diffusion-txt2img.ipynb)                       | Show how to use stable-diffusion v2.1 model to generate images from prompts on Inferentia 2.                                                                                      | [![Open in AWS Studio](https://studiolab.sagemaker.aws/studiolab.svg)](https://studiolab.sagemaker.aws/import/github/huggingface/optimum-neuron/blob/main/notebooks/stable-diffusion/stable-diffusion-txt2img.ipynb)    |
| [How to generate images with Stable Diffusion XL](https://github.com/huggingface/optimum-neuron/blob/main/notebooks/stable-diffusion/stable-diffusion-xl-txt2img.ipynb)                 | Show how to use stable-diffusion XL model to generate images from prompts on Inferentia 2.                                                                                        | [![Open in AWS Studio](https://studiolab.sagemaker.aws/studiolab.svg)](https://studiolab.sagemaker.aws/import/github/huggingface/optimum-neuron/blob/main/notebooks/stable-diffusion/stable-diffusion-xl-txt2img.ipynb) |
| [Compute text embeddings with Sentence Transformers on Inferentia](https://github.com/huggingface/optimum-neuron/blob/main/notebooks/sentence-transformers/getting-started.ipynb)       | Show how to use Sentence Transformers to compute sentence / text embeddings on Inferentia 2.                                                                                      | [![Open in AWS Studio](https://studiolab.sagemaker.aws/studiolab.svg)](https://studiolab.sagemaker.aws/import/github/huggingface/optimum-neuron/blob/main/notebooks/sentence-transformers/getting-started.ipynb)        |
| [How to compile (if needed) and generate text with CodeLlama 7B](https://github.com/huggingface/optimum-neuron/blob/main/notebooks/text-generation/CodeLlama-7B-Compilation.ipynb)      | How to use CodeLlama 7B to generate code. Also walks through compilation.                                                                                                         | [![Open in AWS Studio](https://studiolab.sagemaker.aws/studiolab.svg)](https://studiolab.sagemaker.aws/import/github/huggingface/optimum-neuron/blob/main/notebooks/text-generation/CodeLlama-7B-Compilation.ipynb)     |
| [Compute text embeddings using Qwen3 Embedding models on AWS Trainium](https://github.com/huggingface/optimum-neuron/blob/main/notebooks/feature-extraction/qwen_embedding.ipynb)       | How to run Qwen3 Embedding models on AWS Trainium for feature-extraction / compute text embeddings of sentences.                                                                          | [![Open in AWS Studio](https://studiolab.sagemaker.aws/studiolab.svg)](https://studiolab.sagemaker.aws/import/github/huggingface/optimum-neuron/blob/main/notebooks/feature-extraction/qwen_embedding.ipynb)            |