Gregor Betz's picture

Gregor Betz PRO

ggbetz

·

https://gregorbetz.de

AI & ML interests

Reasoning, AGI, AI Safety, AI Reliability

Recent Activity

posted an update about 5 hours ago

We've just released syncIALO -- a multi-purpose synthetic debate and argument mapping corpus with more than 600k arguments: 📝 Blog article: https://huggingface.co/blog/ggbetz/introducing-syncialo 🛢️ Dataset: https://huggingface.co/datasets/DebateLabKIT/syncialo-raw 👩‍💻 Code: https://github.com/debatelab/syncIALO 🤗 Hugging Face has sponsored the syncIALO project through inference time / compute credits. 🙏 We gratefully acknowledge the generous support. 🫶

updated a dataset about 5 hours ago

DebateLabKIT/syncialo-raw

published a dataset about 5 hours ago

DebateLabKIT/syncialo-raw

View all activity

Articles

syncIAL🍏

about 5 hours ago

Introducing the Open Chain of Thought Leaderboard

Organizations

ggbetz's activity

upvoted a collection 29 days ago

OLMo 2

Artifacts for the second set of OLMo models. • 22 items • Updated 29 days ago • 81

upvoted a paper 3 months ago

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

Paper • 2410.02884 • Published Oct 3, 2024 • 53

upvoted an article 10 months ago

Article

Fine-tune Llama 3 with ORPO

By

•

Apr 22, 2024

• 233

upvoted 2 papers about 1 year ago

Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Paper • 2401.01335 • Published Jan 2, 2024 • 64

G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model

Paper • 2312.11370 • Published Dec 18, 2023 • 20

upvoted 2 papers over 1 year ago

Prompting Is Programming: A Query Language for Large Language Models

Paper • 2212.06094 • Published Dec 12, 2022 • 1

Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Paper • 2308.03188 • Published Aug 6, 2023 • 2