Harry-mic

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

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

args

OpenRLHF

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

textgrad

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

reward-bench

RewardBench: the first evaluation tool for reward models.

Value-Augmented-Sampling

alignment-handbook

Robust recipes to align language models with human and AI preferences

ReMax

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

LLM-Extrapolation

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

vllm

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

sdft

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

self-rewarding-lm-pytorch

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

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.

CUT

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

reid-strong-baseline

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

models

Models and examples built with TensorFlow

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.

TREvaL

Reasonable Reward Evaluation of Large Language Models

alpaca_eval

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

Dromedary

Dromedary: towards helpful, ethical and reliable LLMs.

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".

CycAug

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

LLM-Agent-Paper-Digest

papers related to LLM-agent that published on top conferences

promptbench

A unified evaluation framework for large language models

RL-ViGen

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

DA-in-visualRL

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

safe-rlhf

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

la-mbda

LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization

DI-adventure

Decision Intelligence Adventure for Beginners