This is a curated list of "Embodied AI or robot with Large Language Models" research. Watch this repository for the latest updates! 🔥

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and cont…

A lightweight library for generating synthetic instruction tuning datasets for your data without GPT.

Incorporating Agile methodology into agents to create complex real-world softwares

🙌 OpenHands: Code Less, Make More

Adaptive Swarm Retrieval: A Hierarchical Agent-Based Approach for Blind and Stateful Information Retrieval

The repository for all Azure OpenAI Samples complementing the OpenAI cookbook.

Code for paper "Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement​", Neurips 2023

A collection of benchmarks and datasets for evaluating LLM.

From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :)

The official Meta Llama 3 GitHub site

In Generative AI with Large Language Models (LLMs), you’ll learn the fundamentals of how generative AI works, and how to deploy it in real-world applications.

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…

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Self-Supervised Euphemism Detection and Identification for Content Moderation, IEEE S&P (Oakland) 2021

Deep learning based content moderation from text, audio, video & image input modalities.

The world's largest social media toxicity dataset.

This repo contains the code for generating the ToxiGen dataset, published at ACL 2022.

Finetune LLM to convert an invoice or receipt image to receipt XML or JSON object.

Enforce the output format (JSON Schema, Regex etc) of a language model

Use commands in English to control Blender with OpenAI's GPT-4

Grok open release

Refine high-quality datasets and visual AI models

Patient Flow Analysis using Sankey Plotly Diagram

MedAlign is a clinician-generated dataset for instruction following with electronic medical records.

A machine learning software for extracting information from scholarly documents

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377