shizhediao

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

RLHFlow.github.io

Webpage for RLHFlow

HPT

HPT - Open Multimodal LLMs from HyperGAI

torchtune

A Native-PyTorch Library for LLM Fine-tuning

llama3

The official Meta Llama 3 GitHub site

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

reward-bench

RewardBench: the first evaluation tool for reward models.

OpenDevin

🐚 OpenDevin: Code Less, Make More

bootstrapped-preference-optimization-BPO-

code for "Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization"

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

sleeper-agents-paper

Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".

MLLM-protector

The official repository for paper "MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance"

Directional-Preference-Alignment

Directional Preference Alignment

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Multi-LoRA-Composition

Repository for the Paper "Multi-LoRA Composition for Image Generation"

Automate-CoT

Findings of EMNLP 2023

UniTime

UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting (WWW 2024)

R2PE

GradSafe

Official Code for ACL 2024 paper "GradSafe: Detecting Unsafe Prompts for LLMs via Safety-Critical Gradient Analysis"

ChemistryHTMLPaperParser

Convert HTML/XML Chemistry/Material Science articles into plain text

ConstraintChecker

Official code repository for the EACL2024 paper "ConstraintChecker: A Plugin for Large Language Models to Reason on Commonsense Knowledge Bases"

Awesome-Scientific-Language-Models

A Curated List of Language Models in Scientific Domains

alphageometry

Contamination_For_PreTraining

The source code for the paper contamination analysis for pre-training language models.

tianshou

An elegant PyTorch deep reinforcement learning library.

magicoder

Magicoder: Source Code Is All You Need

CoDA_NeurIPS2023

Official code for NeurIPS2023 paper: CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection

doremi

Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets

promptbench

A unified evaluation framework for large language models