Giovanni Puccetti's repositories
CLIP_benchmark
CLIP-like model evaluation
composer
Train neural networks up to 7x faster
datasets
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
detect-gpt
DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
dinov2
PyTorch code and models for the DINOv2 self-supervised learning method.
fmengine
Utilities for Training Very Large Models
gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
Greek-Document-Search-Engine
The Greek Document Search Engine is a powerful search tool designed for querying large databases of Greek documents. This project utilizes advanced natural language processing (NLP) and machine learning techniques to provide accurate search results from a selection of pre-indexed texts with Faiss.
img2dataset
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
llama
Inference code for LLaMA models
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
llm-foundry
LLM training code for MosaicML foundation models
lm-evaluation-harness
A framework for few-shot evaluation of language models.
MDEL
Multi-Domain Expert Layers
Megatron-LM
Ongoing research training transformer models at scale
QuaPy
A framework for Quantification written in Python
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.