Harry-mic

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

alignment-handbook

Robust recipes to align language models with human and AI preferences

promptbench

A unified evaluation framework for large language models

OpenRLHF

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

self-rag

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.

textgrad

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

alpaca_eval

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

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

safe-rlhf

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Dromedary

Dromedary: towards helpful, ethical and reliable LLMs.

reward-bench

RewardBench: the first evaluation tool for reward models.

Finetune_LLAMA

简单易懂的LLaMA微调指南。

Stable-Alignment

Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".

LLM-Agent-Paper-Digest

papers related to LLM-agent that published on top conferences

Visual-Adversarial-Examples-Jailbreak-Large-Language-Models

Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models

ReMax

Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)

RL-ViGen

This is the repo of "RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization"

sdft

[ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".

DA-in-visualRL

Collection of papers and resources for data augmentation (DA) in visual reinforcement learning (RL).

LLM-Extrapolation

Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"

CUT

Source code of "Reasons to Reject? Aligning Language Models with Judgments"

args

Value-Augmented-Sampling

RE-Control

tdpo

[ICML 2024] Code for the paper "Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases"

TREvaL

Reasonable Reward Evaluation of Large Language Models

CycAug

[NeurIPS 2023] CycAug implementation from paper 'Learning Better with Less: Effective Augmentation for Sample-Efficient Visual RL'.

models

Models and examples built with TensorFlow

reid-strong-baseline

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.