Search Results - RepositoryStats

668

7.7k

mit

143

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

transformers deep-learning human-feedback attention-mechanisms reinforcement-learning artificial-intelligence

Created 2022-12-09

128 commits to main branch, last one 9 months ago

awesome-RLHF opendilab

211

3.4k

apache-2.0

62

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

rlhf deep-learning human-feedback large-language-models reinforcement-learning deep-reinforcement-learning

Created 2023-02-13

63 commits to main branch, last one 9 days ago

LaMDA-rlhf-pytorch conceptofmind

76

466

mit

22

Open-source pre-training implementation of Google's LaMDA in PyTorch. Adding RLHF similar to ChatGPT.

transformers deep-learning human-feedback machine-learning attention-mechanism reinforcement-learning artificial-intelligence

This repository has been archived (exclude archived)

Created 2022-06-21

88 commits to main branch, last one 8 months ago

data-is-better-together huggingface

29

201

unknown

7

Let's build better datasets, together!

datasets community human-feedback machine-learning

Created 2024-03-11

113 commits to main branch, last one 3 months ago

instructGOOSE xrsrke

21

169

mit

4

Implementation of Reinforcement Learning from Human Feedback (RLHF)

rlhf chatgpt instructgpt human-feedback reinforcement-learning

Created 2022-12-28

76 commits to main branch, last one about a year ago

d3po yk7333

14

168

mit

7

[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"

human-feedback diffusion-models reinforcement-learning

Created 2023-11-23

37 commits to main branch, last one 7 months ago

ParroT wxjiao

24

167

unknown

2

The ParroT framework to enhance and regulate the Translation Abilities during Chat based on open-sourced LLMs (e.g., LLaMA-7b, Bloomz-7b1-mt) and human written translation and evaluation data.

lora gpt-4 llama bloomz chatgpt contrastive error-guided human-feedback instruction-tuning machine-translation

Created 2023-03-22

177 commits to master branch, last one about a year ago

trubrics-sdk trubrics

25

131

apache-2.0

5

Product analytics for AI Assistants

llm mlops llmops streamlit ml-monitoring human-feedback model-feedback machine-learning

Created 2022-01-19

939 commits to main branch, last one 5 months ago

beavertails PKU-Alignment

5

110

apache-2.0

5

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

gpt llm llms rlhf llama beaver safety datasets ai-safety safe-rlhf human-feedback language-model human-feedback-data large-language-model

Created 2023-06-14

3 commits to main branch, last one about a year ago

dataset-viber davidberenstein1957

12

42

apache-2.0

1

Dataset Viber is your chill repo for data collection, annotation and vibe checks.

evaluation data-quality human-feedback data-collection

Created 2024-08-07

181 commits to main branch, last one 2 months ago

prism-alignment HannahKirk

1

37

unknown

2

The Prism Alignment Project

dataset alignment multicultural human-feedback sociotechnical human-feedback-data

Created 2024-03-06

12 commits to main branch, last one 6 months ago

Reliable_AD ZhenbangDu

0

34

unknown

3

[ECCV2024] Towards Reliable Advertising Image Generation Using Human Feedback

rlhf datasets eccv2024 diffusers diffusion advertising human-feedback diffusion-models image-generation

Created 2024-07-04

41 commits to main branch, last one 2 months ago

tdpo ZiyiZhang27

0

29

mit

2

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

rlhf alignment text-to-image human-feedback diffusion-models stable-diffusion reinforcement-learning

Created 2024-05-19

6 commits to main branch, last one 3 months ago

prelude gao-g

0

25

mit

3

Code for the paper "Aligning LLM Agents by Learning Latent Preference from User Edits".

llm gpt4 llms edits alignment transformers user-feedback human-feedback interpretability preference-learning

Created 2024-04-25

14 commits to main branch, last one 16 days ago