Search Results - RepositoryStats

70

1.1k

apache-2.0

12

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

ai llms rlhf rlaif openai python huggingface synthetic-data synthetic-dataset-generation

Created 2023-10-16

618 commits to main branch, last one 5 days ago

awesome-RLAIF mengdi-li

3

88

apache-2.0

3

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

rl llms rlhf rlaif alignment

Created 2023-09-17

36 commits to main branch, last one 2 days ago

zero-shot-reward-models vicgalle

7

32

mit

2

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

llm rlhf trlx rlaif zero-shot reward-models reinforcement-learning

Created 2023-03-03

21 commits to main branch, last one 10 months ago

Prompt-OIRL holarissun

5

25

mit

2

code for paper Query-Dependent Prompt Evaluation and Optimization with Offline Inverse Reinforcement Learning

irl llm rlhf rlaif offline-rl offline-irl prompt-engineering large-language-models inverse-reinforcement-learning

Created 2023-09-10

58 commits to main branch, last one 3 months ago