A course on aligning smol models.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

Event-driven Infrastructure for Modern Cloud

💪🏻 system monitoring on steroids

🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.

Bare metal to production ready in mins; your own fly server on your VPS.

✨ Innovative and open-source visualization application that transforms various data formats, such as JSON, YAML, XML, CSV and more, into interactive graphs.

An extremely fast Python package and project manager, written in Rust.

A toolkit to create optimal Production-readyRetrieval Augmented Generation(RAG) setup for your data

An open-source, lightweight note-taking solution. The pain-less way to create your meaningful notes. Your Notes, Your Way.

An open-source RAG-based tool for chatting with your documents.

Optimizing inference proxy for LLMs

Things you can do with the token embeddings of an LLM

Code for Quiet-STaR

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

UNet diffusion model in pure CUDA

A collection of guides and examples for the Gemma open models from Google.

The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>

LLM101n: Let's build a Storyteller

[EMNLP 2024] Official PyTorch implementation code for realizing the technical part of Traversal of Layers (TroL) presenting new propagation operation to get super vision language performances.

We write your reusable computer vision tools. 💜

GNN-RAG: Graph Neural Retrieval for Large Language Modeling Reasoning

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

llama3 implementation one matrix multiplication at a time