Hugo Sousa's starred repositories
python-fire
Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.
LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
ml-engineering
Machine Learning Engineering Open Book
TensorRT-LLM
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
lm-evaluation-harness
A framework for few-shot evaluation of language models.
LLM-Agent-Paper-List
The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
promptbase
All things prompt engineering
PurpleLlama
Set of tools to assess and improve LLM security.
Megatron-DeepSpeed
Ongoing research training transformer language models at scale, including: BERT & GPT-2
deep-translator
A flexible free and unlimited python tool to translate between different languages in a simple way using multiple translators.
latexindent.pl
Perl script to add indentation (leading horizontal space) to LaTeX files. It can modify line breaks before, during and after code blocks; it can perform text wrapping and paragraph line break removal. It can also perform string-based and regex-based substitutions/replacements. The script is customisable through its YAML interface.
annotated-s4
Implementation of https://srush.github.io/annotated-s4
croissant-llm-training
Repository containing the code for training the CroissantLLM
CQE_Evaluation
Evaluation script for CQE framework
PT-Pump-Up
Hub for the Portuguese language NLP Resources