ChangyuChen347

ChangyuChen347's Stars

• EleutherAI/lm-evaluation-harness

  A framework for few-shot evaluation of language models.

  Language:Python6.9k381.1k1.8k

• OpenRLHF/OpenRLHF

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

  Language:Python2.4k21274233

• tatsu-lab/alpaca_eval

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

  Language:Jupyter Notebook1.5k8143239

• hendrycks/test

  Measuring Massive Multitask Language Understanding | ICLR 2021

  Language:Python1.2k192090

• princeton-nlp/SimPO

  [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

  Language:Python69687045

• hsiehjackson/RULER

  This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

  Language:Python644155743

• lmarena/arena-hard-auto

  Arena-Hard-Auto: An automatic LLM benchmark.

  Language:Jupyter Notebook62372771

• corl-team/CORL

  High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

  Language:Python47631020

• RLHFlow/Online-RLHF

  A recipe for online RLHF and online iterative DPO.

  Language:Python405182244

• LiveBench/LiveBench

  LiveBench: A Challenging, Contamination-Free LLM Benchmark

  Language:Python27686724

• p-lambda/dsir

  DSIR large-scale data selection framework for language model training

  Language:Python22721719

• Psycoy/MixEval

  The official evaluation suite and dynamic data release for MixEval.

  Language:Python22212934

• TIGER-AI-Lab/MAmmoTH2

  Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]

  Language:Python123399

• openpsi-project/ReaLHF

  Super-Efficient RLHF Training of LLMs with Parameter Reallocation

  Language:Python1083174

• Vance0124/Token-level-Direct-Preference-Optimization

  Reference implementation for Token-level Direct Preference Optimization(TDPO)

  Language:Python991710

• snu-mllab/EDAC

  Official PyTorch implementation of "Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble" (NeurIPS'21)

  Language:Python71225

• chujiezheng/LLM-Extrapolation

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

  Language:Python66512

• shenao-zhang/SELM

  The official implementation of Self-Exploring Language Models (SELM)

  Language:Python56127

• hamishivi/EasyLM

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

  Language:Python541013

• haozheji/exact-optimization

  ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment

  Language:Python46450

• RUCAIBox/JiuZhang3.0

  The code and data for the paper JiuZhang3.0

  Language:Python35021

• thu-ml/Noise-Contrastive-Alignment

  Code accompanying the paper "Noise Contrastive Alignment of Language Models with Explicit Rewards" (NeurIPS 2024)

  Language:Python31843

• VinAIResearch/RecGPT

  RecGPT: Generative Pre-training for Text-based Recommendation (ACL 2024)

  Language:Python28101

• wzhouad/WPO

  Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"

  Language:Python280

• thanhnguyentang/mmdrl

  Official repo for our AAAI'21 paper, https://arxiv.org/abs/2007.12354

  Language:Python25507

• ZhaolinGao/REBEL

  Language:Python25104

• ars22/scaling-LLM-math-synthetic-data

  Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"

  24610

• TsinghuaC3I/Intuitive-Fine-Tuning

  Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process

  Language:Python220

• alecwangcq/f-divergence-dpo

  Direct preference optimization with f-divergences.

  Language:Python11113

• morganf33/GNR

  code for "Generative News Recommendation"

  Language:Python10112