khankindle's Projects
The open-source language model computer
MIT iQuHACK 2022 x Microsoft x IonQ Challenge
š A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
A library of reinforcement learning components and agents
Open-Source AI wearable device and software
š¤ AutoTrain Advanced
A list of AI autonomous agents
Awesome Devin-inspired AI agents
An awesome repository of local AI tools
VSCode inspired watch face for Sense and Versa 3
Copybara: A tool for transforming and moving code between repositories.
This repository is a curated collection of links to various courses and resources about Artificial Intelligence (AI)
These are Github repositories for all data science material I feel important. I would update it daily.
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.
FarmVibes.AI: Multi-Modal GeoSpatial ML Models for Agriculture and Sustainability
flow-pilot is an openpilot based driver assistance system that runs on linux, windows and android powered machines.
AI wearable with 24h+ battery
Training LLMs with QLoRA + FSDP
Graph Machine Learning course, Xavier Bresson, 2023
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
The bare metal in my basement
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."
Reaching LLaMA2 Performance with 0.1M Dollars