natolambert

OpenRLHF

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

Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

elevenlabs-python

The official Python API for ElevenLabs Text to Speech.

PufferLib

Simplifying reinforcement learning for complex game environments

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

nomic

Interact, analyze and structure massive text, image, embedding, audio and video datasets

RLHF-Reward-Modeling

Recipes to train reward model for RLHF.

awesome-o1

A bibliography and survey of the papers surrounding o1

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

DataDreamer

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

MAP-NEO

arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

OLMoE

OLMoE: Open Mixture-of-Experts Language Models

PickScore

rlhf-book

Textbook on reinforcement learning from human feedback

pandoc-book-template

A simple Pandoc template to build documents and ebooks.

smol-podcaster

smol-podcaster is your podcast production agent 🎙️

RLAIF-V

[CVPR'25] RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness

awesome-open-source-lms

Friends of OLMo and their links.

WildBench

Benchmarking LLMs with Challenging Tasks from Real Users

LLMBar

[ICLR 2024] Evaluating Large Language Models at Evaluating Instruction Following

maya

Maya: An Instruction Finetuned Multilingual Multimodal Model using Aya

wildguard

Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

async_rlhf

Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models

adapt-demos

Lightweight tools for quick and easy LLM demo's

m-rewardbench

Official Code for M-RᴇᴡᴀʀᴅBᴇɴᴄʜ: Evaluating Reward Models in Multilingual Settings

general-preference-model

Official implementation of paper "Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment" (https://arxiv.org/abs/2410.02197)

noncompliance

This repository contains data, code and models for contextual noncompliance.

tr-gy-8013-Fa-24

Course material for Fall 24 Deep Learning for Urban Systems Course