Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

Modern C++ Programming Course (C++03/11/14/17/20/23/26)

Versatile computational pipeline for processing protein structure data for deep learning applications.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Plain pytorch implementation of LLaMA

This repository contains tutorials and examples for Triton Inference Server

Flash Attention in ~100 lines of CUDA (forward pass only)

LLM training in simple, raw C/CUDA

Tile primitives for speedy kernels

Turn any glasses into AI-powered smart glasses

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

Interact with your SQL database, Natural Language to SQL using LLMs

Replace OpenAI with Llama.cpp Automagically.

Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

Deploy and scale serverless machine learning app - in 4 steps.

AdalFlow: The library to build & auto-optimize LLM applications.

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

MINT-1T: A one trillion token multimodal interleaved dataset.

C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX for x86/x64, NEON for ARM.

Things you can do with the token embeddings of an LLM

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains