Practical Llama 3 inference in Java

Inference Llama 2 in one file of pure Java

Inference Llama 2 in one file of pure C

LLM101n: Let's build a Storyteller

A simple RAG application for doing question-answering on a PDF document. Uses the PyCharm documentation as the source document and langchain to build the RAG pipeline.

Inference Llama 2 in one file of pure Python

Llama 2 inference in one file of pure Go