rlhf | Topic | Ecosyste.ms: Repos

Topic: "rlhf"

hiyouga/LLaMA-Factory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Language: Python - Size: 44 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 46,849 - Forks: 5,727

LAION-AI/Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Language: Python - Size: 33.8 MB - Last synced at: 6 days ago - Pushed at: 8 months ago - Stars: 37,294 - Forks: 3,268

RUCAIBox/LLMSurvey

The official GitHub page for the survey paper "A Survey of Large Language Models".

Language: Python - Size: 43.1 MB - Last synced at: 2 days ago - Pushed at: about 1 month ago - Stars: 11,383 - Forks: 882

ymcui/Chinese-LLaMA-Alpaca-2

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

Language: Python - Size: 8.15 MB - Last synced at: 2 days ago - Pushed at: 7 months ago - Stars: 7,159 - Forks: 572

InternLM/InternLM

Official release of InternLM2 7B and 20B base and chat models. 200K context support

Language: Python - Size: 4.52 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 5,395 - Forks: 383

huggingface/alignment-handbook

Robust recipes to align language models with human and AI preferences

Language: Python - Size: 255 KB - Last synced at: about 17 hours ago - Pushed at: 5 months ago - Stars: 5,134 - Forks: 442

argilla-io/argilla

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

Language: Python - Size: 772 MB - Last synced at: 10 days ago - Pushed at: 14 days ago - Stars: 4,438 - Forks: 420

opendilab/awesome-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

Size: 471 KB - Last synced at: 11 days ago - Pushed at: 2 months ago - Stars: 3,873 - Forks: 237

hiyouga/ChatGLM-Efficient-Tuning 📦

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

Language: Python - Size: 194 MB - Last synced at: about 1 month ago - Pushed at: over 1 year ago - Stars: 3,693 - Forks: 474

Kiln-AI/Kiln

The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.

Language: Python - Size: 14.3 MB - Last synced at: 2 days ago - Pushed at: 2 days ago - Stars: 3,391 - Forks: 235

PKU-Alignment/align-anything

Align Anything: Training All-modality Model with Feedback

Language: Jupyter Notebook - Size: 108 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 3,340 - Forks: 398

Docta-ai/docta

A Doctor for your data

Language: Python - Size: 27.8 MB - Last synced at: 11 days ago - Pushed at: 3 months ago - Stars: 3,098 - Forks: 231

argilla-io/distilabel

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Language: Python - Size: 543 MB - Last synced at: 2 days ago - Pushed at: 7 days ago - Stars: 2,640 - Forks: 193

transformerlab/transformerlab-app

Open Source Application for Advanced LLM Engineering: interact, train, fine-tune, and evaluate large language models on your own computer.

Language: TypeScript - Size: 9.37 MB - Last synced at: 4 days ago - Pushed at: 5 days ago - Stars: 1,964 - Forks: 109

tatsu-lab/alpaca_eval

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

Language: Jupyter Notebook - Size: 302 MB - Last synced at: 8 days ago - Pushed at: 4 months ago - Stars: 1,716 - Forks: 266

THUDM/WebGLM

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

Language: Python - Size: 6.19 MB - Last synced at: 8 days ago - Pushed at: 27 days ago - Stars: 1,585 - Forks: 139

PKU-Alignment/safe-rlhf

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

Language: Python - Size: 3.99 MB - Last synced at: 2 days ago - Pushed at: 10 months ago - Stars: 1,448 - Forks: 120

THUDM/ImageReward

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

Language: Python - Size: 4.18 MB - Last synced at: 11 days ago - Pushed at: 3 months ago - Stars: 1,369 - Forks: 71

OpenLMLab/MOSS-RLHF

Secrets of RLHF in Large Language Models Part I: PPO

Language: Python - Size: 2.5 MB - Last synced at: 13 days ago - Pushed at: about 1 year ago - Stars: 1,350 - Forks: 98

ContextualAI/HALOs

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Language: Python - Size: 5.25 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 830 - Forks: 51

xtreme1-io/xtreme1

Xtreme1 is an all-in-one data labeling and annotation platform for multimodal data training and supports 3D LiDAR point cloud, image, and LLM.

Language: TypeScript - Size: 49.8 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 743 - Forks: 117

GaryYufei/AlignLLMHumanSurvey

Aligning Large Language Models with Human: A Survey

Size: 335 KB - Last synced at: 2 days ago - Pushed at: over 1 year ago - Stars: 727 - Forks: 32

natolambert/rlhf-book

Textbook on reinforcement learning from human feedback

Language: TeX - Size: 6.88 MB - Last synced at: about 19 hours ago - Pushed at: about 20 hours ago - Stars: 658 - Forks: 59

jerry1993-tech/Cornucopia-LLaMA-Fin-Chinese

聚宝盆(Cornucopia): 中文金融系列开源可商用大模型，并提供一套高效轻量化的垂直领域LLM训练框架(Pretraining、SFT、RLHF、Quantize等)

Language: Python - Size: 1.64 MB - Last synced at: 2 days ago - Pushed at: almost 2 years ago - Stars: 626 - Forks: 64

jianzhnie/LLamaTuner

Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.

Language: Python - Size: 1.02 MB - Last synced at: 2 days ago - Pushed at: 3 months ago - Stars: 600 - Forks: 63

voidful/TextRL

Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

Language: Python - Size: 400 KB - Last synced at: 12 days ago - Pushed at: 12 months ago - Stars: 556 - Forks: 59

RLHFlow/Online-RLHF

A recipe for online RLHF and online iterative DPO.

Language: Python - Size: 249 KB - Last synced at: 2 days ago - Pushed at: 4 months ago - Stars: 507 - Forks: 46

uclaml/SPPO

The official implementation of Self-Play Preference Optimization (SPPO)

Language: Python - Size: 3 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 463 - Forks: 47

mindspore-courses/step_into_llm

MindSpore online courses: Step into LLM

Language: Jupyter Notebook - Size: 246 MB - Last synced at: 2 days ago - Pushed at: 4 months ago - Stars: 457 - Forks: 111

CambioML/pykoi-rlhf-finetuned-transformers

pykoi: Active learning in one unified interface

Language: Jupyter Notebook - Size: 54.1 MB - Last synced at: 17 days ago - Pushed at: about 1 year ago - Stars: 410 - Forks: 44

Joyce94/LLM-RLHF-Tuning

LLM Tuning with PEFT (SFT+RM+PPO+DPO with LoRA)

Language: Python - Size: 22.3 MB - Last synced at: 2 days ago - Pushed at: over 1 year ago - Stars: 409 - Forks: 17

glgh/awesome-llm-human-preference-datasets

A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.

Size: 11.7 KB - Last synced at: 2 days ago - Pushed at: over 1 year ago - Stars: 353 - Forks: 15

sail-sg/oat

🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.

Language: Python - Size: 2.27 MB - Last synced at: 3 days ago - Pushed at: 3 days ago - Stars: 325 - Forks: 21

WangRongsheng/MedQA-ChatGLM 📦

🛰️ 基于真实医疗对话数据在ChatGLM上进行LoRA、P-Tuning V2、Freeze、RLHF等微调，我们的眼光不止于医疗问答

Language: Python - Size: 20.7 MB - Last synced at: about 24 hours ago - Pushed at: over 1 year ago - Stars: 322 - Forks: 49

TUDB-Labs/mLoRA

An Efficient "Factory" to Build Multiple LoRA Adapters

Language: Python - Size: 11 MB - Last synced at: 7 days ago - Pushed at: 2 months ago - Stars: 307 - Forks: 58

Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope and StableVideoDiffusion by finetuning them using various reward models such as HPS, PickScore, VideoMAE, VJEPA, YOLO, Aesthetics etc.

Language: Python - Size: 164 MB - Last synced at: 24 days ago - Pushed at: about 1 month ago - Stars: 253 - Forks: 15

jianzhnie/Open-R1

The open source implementation of DeepSeek-R1. 开源复现 DeepSeek-R1

Language: Python - Size: 1.02 MB - Last synced at: 2 days ago - Pushed at: about 1 month ago - Stars: 253 - Forks: 47

haoliuhl/chain-of-hindsight

Simple next-token-prediction for RLHF

Language: Python - Size: 162 KB - Last synced at: 18 days ago - Pushed at: over 1 year ago - Stars: 223 - Forks: 17

jackaduma/Vicuna-LoRA-RLHF-PyTorch

A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Vicuna architecture. Basically ChatGPT but with Vicuna

Language: Python - Size: 18.7 MB - Last synced at: 8 days ago - Pushed at: 11 months ago - Stars: 213 - Forks: 19

jasonvanf/llama-trl

LLaMA-TRL: Fine-tuning LLaMA with PPO and LoRA

Language: Python - Size: 37.1 MB - Last synced at: 2 days ago - Pushed at: almost 2 years ago - Stars: 211 - Forks: 23

THUDM/VisionReward

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

Language: Python - Size: 9.97 MB - Last synced at: 26 days ago - Pushed at: 26 days ago - Stars: 194 - Forks: 4

tomekkorbak/pretraining-with-human-feedback

Code accompanying the paper Pretraining Language Models with Human Preferences

Language: Python - Size: 135 KB - Last synced at: 21 days ago - Pushed at: about 1 year ago - Stars: 180 - Forks: 14

xrsrke/instructGOOSE

Implementation of Reinforcement Learning from Human Feedback (RLHF)

Language: Jupyter Notebook - Size: 3.31 MB - Last synced at: 12 days ago - Pushed at: about 2 years ago - Stars: 172 - Forks: 21

TideDra/VL-RLHF

A RLHF Infrastructure for Vision-Language Models

Language: Python - Size: 3.8 MB - Last synced at: 4 days ago - Pushed at: 5 months ago - Stars: 171 - Forks: 7

PKU-Alignment/aligner

[NeurIPS 2024 Oral] Aligner: Efficient Alignment by Learning to Correct

Language: Python - Size: 16.3 MB - Last synced at: 2 days ago - Pushed at: 3 months ago - Stars: 169 - Forks: 8

YangLing0818/IterComp

[ICLR 2025] IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation

Language: Python - Size: 32.8 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 161 - Forks: 10

mengdi-li/awesome-RLAIF

A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)

Size: 313 KB - Last synced at: 10 days ago - Pushed at: 3 months ago - Stars: 160 - Forks: 4

allenai/reward-bench

RewardBench: the first evaluation tool for reward models.

Language: Python - Size: 3.29 MB - Last synced at: about 1 year ago - Pushed at: about 1 year ago - Stars: 157 - Forks: 15

liziniu/ReMax

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

Language: Python - Size: 1.76 MB - Last synced at: 5 months ago - Pushed at: over 1 year ago - Stars: 151 - Forks: 13

HarderThenHarder/RLLoggingBoard

A visuailzation tool to make deep understaning and easier debugging for RLHF training.

Language: Python - Size: 6.26 MB - Last synced at: about 2 months ago - Pushed at: 2 months ago - Stars: 147 - Forks: 5

RLHFlow/RLHF-Reward-Modeling

A recipe to train reward models for RLHF.

Language: Python - Size: 143 KB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 143 - Forks: 7

PKU-Alignment/beavertails

BeaverTails is a collection of datasets designed to facilitate research on safety alignment in large language models (LLMs).

Language: Makefile - Size: 2.34 MB - Last synced at: 2 days ago - Pushed at: over 1 year ago - Stars: 134 - Forks: 6

jackaduma/ChatGLM-LoRA-RLHF-PyTorch

A full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the ChatGLM architecture. Basically ChatGPT but with ChatGLM

Language: Python - Size: 25.3 MB - Last synced at: 2 days ago - Pushed at: almost 2 years ago - Stars: 134 - Forks: 10

opening-up-chatgpt/opening-up-chatgpt.github.io

Tracking instruction-tuned LLM openness. Paper: Liesenfeld, Andreas, Alianda Lopez, and Mark Dingemanse. 2023. “Opening up ChatGPT: Tracking Openness, Transparency, and Accountability in Instruction-Tuned Text Generators.” In Proceedings of the 5th International Conference on Conversational User Interfaces. doi:10.1145/3571884.3604316.

Language: Python - Size: 1.51 MB - Last synced at: 6 days ago - Pushed at: about 1 month ago - Stars: 117 - Forks: 7

l294265421/alpaca-rlhf

Finetuning LLaMA with RLHF (Reinforcement Learning with Human Feedback) based on DeepSpeed Chat

Language: Python - Size: 97.9 MB - Last synced at: 2 days ago - Pushed at: almost 2 years ago - Stars: 115 - Forks: 14

csmile-1006/PreferenceTransformer

Preference Transformer: Modeling Human Preferences using Transformers for RL (ICLR2023 Accepted)

Language: Python - Size: 25.6 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 107 - Forks: 13

NiuTrans/Vision-LLM-Alignment

This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.

Language: Python - Size: 153 MB - Last synced at: 15 days ago - Pushed at: 6 months ago - Stars: 104 - Forks: 8

log10-io/log10

Python client library for improving your LLM app accuracy

Language: Python - Size: 16.6 MB - Last synced at: 10 days ago - Pushed at: 2 months ago - Stars: 97 - Forks: 11

yihedeng9/rlhf-summary-notes

A brief and partial summary of RLHF algorithms.

Size: 4.02 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 96 - Forks: 2

nlp-uoregon/Okapi

Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback

Language: Python - Size: 262 MB - Last synced at: 2 days ago - Pushed at: over 1 year ago - Stars: 94 - Forks: 2

Miraclemarvel55/ChatGLM-RLHF

对ChatGLM直接使用RLHF提升或降低目标输出概率|Modify ChatGLM output with only RLHF

Language: Python - Size: 932 KB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 87 - Forks: 13

cogment/cogment-verse

Research platform for Human-in-the-loop learning (HILL) & Multi-Agent Reinforcement Learning (MARL)

Language: Python - Size: 19.7 MB - Last synced at: 8 days ago - Pushed at: over 1 year ago - Stars: 81 - Forks: 17

jackaduma/Alpaca-LoRA-RLHF-PyTorch

A full pipeline to finetune Alpaca LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the Alpaca architecture. Basically ChatGPT but with Alpaca

Language: Python - Size: 18.7 MB - Last synced at: 2 days ago - Pushed at: almost 2 years ago - Stars: 58 - Forks: 6

RLHFlow/Directional-Preference-Alignment

Directional Preference Alignment

Size: 1.83 MB - Last synced at: 4 days ago - Pushed at: 7 months ago - Stars: 57 - Forks: 3

jackfsuia/nanoRLHF

RLHF experiments on a single A100 40G GPU. Support PPO, GRPO, REINFORCE, RAFT, RLOO, ReMax, DeepSeek R1-Zero reproducing.

Language: Python - Size: 2 MB - Last synced at: 12 days ago - Pushed at: 2 months ago - Stars: 54 - Forks: 11

QuentinWach/image-ranker

Rank images using TrueSkill by comparing them against each other in the browser. 🖼📊

Language: HTML - Size: 9.86 MB - Last synced at: 18 days ago - Pushed at: 4 months ago - Stars: 52 - Forks: 9

sail-sg/dice

Official implementation of Bootstrapping Language Models via DPO Implicit Rewards

Language: Python - Size: 18.4 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 43 - Forks: 3

holarissun/RewardModelingBeyondBradleyTerry

official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and Alternatives

Language: Python - Size: 365 MB - Last synced at: 19 days ago - Pushed at: 19 days ago - Stars: 41 - Forks: 3

snu-mllab/DPPO

Official implementation of "Direct Preference-based Policy Optimization without Reward Modeling" (NeurIPS 2023)

Language: Python - Size: 26.5 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 35 - Forks: 1

ZiyiZhang27/tdpo

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

Language: Python - Size: 3.28 MB - Last synced at: 1 day ago - Pushed at: 9 months ago - Stars: 35 - Forks: 0

haozheji/exact-optimization

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

Language: Python - Size: 188 KB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 35 - Forks: 1

CIntellifusion/VideoDPO

Official Implementation of VideoDPO

Language: Python - Size: 20.6 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 34 - Forks: 0

ZhenbangDu/Reliable_AD

[ECCV2024] Towards Reliable Advertising Image Generation Using Human Feedback

Language: Python - Size: 3.92 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 34 - Forks: 0

vicgalle/zero-shot-reward-models

ZYN: Zero-Shot Reward Models with Yes-No Questions

Language: Python - Size: 1.3 MB - Last synced at: about 2 months ago - Pushed at: over 1 year ago - Stars: 33 - Forks: 8

dobriban/Principles-of-AI-LLMs

Materials for the course Principles of AI: LLMs at UPenn (Stat 9911, Spring 2025). LLM architectures, training paradigms (pre- and post-training, alignment), test-time computation, reasoning, safety and robustness (jailbreaking, oversight, uncertainty), representations, interpretability (circuits), etc.

Size: 157 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 30 - Forks: 0