Aakash Apoorv's repositories
build-nanogpt
Video+code lecture on building nanoGPT from scratch
chatty
ChattyUI - your private AI chat for running LLMs in the browser
DiffusionKit
On-device Inference of Diffusion Models for Apple Silicon
DL4AGX
Deep Learning tools and applications for NVIDIA AGX platforms.
embedchain
Memory for AI agents
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
flax
Flax is a neural network library for JAX that is designed for flexibility.
gpt-fast
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
HolisticTraceAnalysis
A library to analyze PyTorch traces.
inspectus
LLM Analytics
jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
LibCST
A concrete syntax tree parser and serializer library for Python that preserves many aspects of Python's abstract syntax tree
LivePortrait
Bring portraits to life!
LLM101n
LLM101n: Let's build a Storyteller
LookOnceToHear
A novel human-interaction method for real-time speech extraction on headphones.
MiniCPM-V
MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone
nilearn
Machine learning for NeuroImaging in Python
Perplexica
Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI
searxng
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
Stirling-PDF
#1 Locally hosted web application that allows you to perform various operations on PDF files
TKAN
TKAN: Temporal Kolmogorov-Arnold Networks
torch2trt
An easy to use PyTorch to TensorRT converter
torchfix
TorchFix - a linter for PyTorch-using code with autofix support
torchtitan
A native PyTorch Library for large model training
transformers.js
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
trl
Train transformer language models with reinforcement learning.
tutel
Tutel MoE: An Optimized Mixture-of-Experts Implementation