ovcharenkoo

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

chatbot-ui

AI chat for every model.

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Scrapegraph-ai

Python scraper based on AI

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

text-generation-inference

Large Language Model Text Generation Inference

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

lm-evaluation-harness

A framework for few-shot evaluation of language models.

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

lectures

Material for cuda-mode lectures

FeatUp

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

deepops

Tools for building GPU clusters

open-gpu-kernel-modules

NVIDIA Linux open GPU with P2P support

tensorrtllm_backend

The Triton TensorRT-LLM Backend

tutorials

This repository contains tutorials and examples for Triton Inference Server

json_repair

A python module to repair invalid JSON, commonly used to parse the output of LLMs

NeMo-Aligner

Scalable toolkit for efficient model alignment

NeMo-Curator

Scalable toolkit for data curation

modulus-makani

Massively parallel training of machine-learning based weather and climate models

cartography

Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics

earth2mip

Earth-2 Model Intercomparison Project (MIP) is a python framework that enables climate researchers and scientists to inter-compare AI models for weather and climate.

modulus-sym

Framework providing pythonic APIs, algorithms and utilities to be used with Modulus core to physics inform model training as well as higher level abstraction for domain experts

mipt_course

EAGE-Hackathon-2024-Instructions

Here you will find all the info you need to know to participate in the 2024 EAGE Annual Hackathon in Oslo!

rapids-examples