Luca Antiga

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Code for the book Deep Learning with PyTorch by Eli Stevens, Luca Antiga, and Thomas Viehmann.

Retina blood vessel segmentation with a convolutional neural network

A Redis module for serving tensors and executing deep learning graphs