LLM-PowerHouse: Unleash LLMs' potential through curated tutorials, best practices, and ready-to-use code for custom training and inferencing.

leaked prompts of GPTs

A statistical toolkit for scientific discovery using machine learning

Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

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

Script to get your site indexed on Google in less than 48 hours

Automated Evaluation of RAG Systems

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

Fast, memory-efficient, scalable optimization of deep learning with differential privacy

kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)

Resources for Data Centric AI

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Seq2Seq project centered on formality transfer

Code for "Image Generation from Scene Graphs", Johnson et al, CVPR 2018

Graph Auto-Encoder in PyTorch

Implementation of ECCV 2020 paper: "Controllable Image Synthesis via SegVAE". Project page: https://yccyenchicheng.github.io/SegVAE/. Paper: https://arxiv.org/abs/2007.08397.

Reimplementation of Graph Autoencoder by Kipf & Welling with DGL.