A collection of 3D reconstruction papers in the deep learning era.

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

Train transformer language models with reinforcement learning.

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

A DeepLab V3+ Model with choice of Encoder for Binary Segmentation. Implemented with Tensorflow.

PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset.

PyTorch implementation of DeepLabv3

Implementation of the DeepLabV3+ model in PyTorch for semantic segmentation, trained on DeepFashion2 dataset

Must-read Papers on Physics-Informed Neural Networks.

Collection of AWESOME vision-language models for vision tasks

Famous Vision Language Models and Their Architectures

Tutorial on normalizing flows.

Multi-Agent Reinforcement Learning (MARL) papers

Code for Machine Learning for Algorithmic Trading, 2nd edition.

Notes and commented code for RLHF (PPO)

Material for gpu-mode lectures

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Try out deep learning models online on Google Colab

Transformer Explained Visually: Learn How LLM Transformer Models Work with Interactive Visualization

Amazon ML Challenge is a two stage competition where students from all engineering campuses across India will get a unique opportunity to work on Amazon’s dataset to bring in fresh ideas and build …

It is a solution to amazon ml engineer hiring challenge 2020

Chatbot for documentation, that allows you to chat with your data. Privately deployable, provides AI knowledge sharing and integrates knowledge into your AI workflow

A Collection of Variational Autoencoders (VAE) in PyTorch.

Open-Sora: Democratizing Efficient Video Production for All

Multi30k Dataset

Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI

Accessible large language models via k-bit quantization for PyTorch.

QLoRA: Efficient Finetuning of Quantized LLMs