Hashem Alsaket's repositories
prompttools
Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate).
benchmarking_speed
Benchmark the speed of programming languages across practical use cases
bitcoin
Bitcoin Core integration/staging tree
cereal-box-maze-solver
Project focused on auto solving mazes on the back of cereal boxes
HashemAlsaket
Config files for my GitHub profile.
uber-eats-rec-engine
Custom Uber Eats recommendation engine
goldeneye
GoldenEye is a functional simulator with fault injection capabilities for common and emerging numerical formats, implemented for the PyTorch deep learning framework.
langchain
⚡ Building applications with LLMs through composability ⚡
llama.cpp
Port of Facebook's LLaMA model in C/C++
MetisFL
MetisFL is a federated learning framework that allows developers to easily federate their machine learning workflows and train their models across distributed data without ever collecting the data in a centralized location. The core of the framework is written in C++ and focuses on scalability, speed and resiliency.
nix
Nix, the purely functional package manager
PDFProc
PDF processor for extracting data seamlessly for desired formats.
pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
qiskit-terra
Qiskit is an open-source SDK for working with quantum computers at the level of extended quantum circuits, operators, and algorithms.
SummaryInfoLoss
Can we quantify how much information is lost through summarization?
unsloth
Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory