MEND: Fast Model Editing at Scale

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Official Repository for Dataset Inference for LLMs

A collection of LLM related papers, thesis, tools, datasets, courses, open source models, benchmarks

LLM based autonomous agent that conducts local and web research on any topic and generates a comprehensive report with citations.

A curated list of foundation models for vision and language tasks

Virtual whiteboard for sketching hand-drawn like diagrams

A Multitask Framework for Present and Absent Keyphrase Generation using Knowledge Graphs

Awesome LLM compression research papers and tools.

Natural Langauge Processing with Deep Learning - Lectures and exercises

📖 A curated list of resources dedicated to Natural Language Processing (NLP)

💯 Curated coding interview preparation materials for busy software engineers

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

A curated list for Efficient Large Language Models

Large Language Models: In this repository Language models are introduced covering both theoretical and practical aspects.

A package for ontology engineering with deep learning and language models.

QLoRA: Efficient Finetuning of Quantized LLMs

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

PromptKG Family: a Gallery of Prompt Learning & KG-related research works, toolkits, and paper-list.

Must-read papers on prompt-based tuning for pre-trained language models.

A compilation of research advice.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

The data and the PyTorch implementation for the models and experiments in the paper "Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction".