A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Mobile App Tasks with Iterative Feedback (MoTIF): Addressing Task Feasibility in Interactive Visual Environments

Code and Data for "Language Modeling with Editable External Knowledge"

Secrets of RLHF in Large Language Models Part I: PPO

Ongoing research training transformer models at scale

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models (ICLR 2024, Official Implementation)

[NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

Repository for "Propagating Knowledge Updates to LMs Through Distillation" (NeurIPS 2023).

A beautiful, simple, clean, and responsive Jekyll theme for academics

A library for efficient similarity search and clustering of dense vectors.

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

[EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

Code for fine-tuning Platypus fam LLMs using LoRA

Reference implementation for DPO (Direct Preference Optimization)

Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model

Code and documentation to train Stanford's Alpaca models, and generate the data.

Extract addresses and intents from tweet texts

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

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

Google Research

A modular RL library to fine-tune language models to human preferences

A Collection of BM25 Algorithms in Python

Automatic metrics for GEM tasks

The InterScript dataset contains interactive user feedback on scripts generated by a T5-XXL model.

Code for the paper "Simulating Bandit Learning from User Feedback for Extractive Question Answering".