Gregor Betz PRO

ggbetz

·

https://gregorbetz.de

AI & ML interests

Reasoning, AGI, AI Safety, AI Reliability

Recent Activity

updated a dataset about 22 hours ago

ggbetz/cached-reasoning-records

published a dataset 2 days ago

ggbetz/cached-reasoning-records

upvoted an article 18 days ago

SmolLM3: smol, multilingual, long-context reasoner

View all activity

Organizations

New activity in DebateLabKIT/Nemotron-Cascade-14B-Argunaut-2-SFT-LORA-dev2 8 months ago

Add RL training friendly chat template

#1 opened 8 months ago by

New activity in DebateLabKIT/argunauts-thinking about 1 year ago

Upload dataset

#8 opened about 1 year ago by

Upload dataset

#7 opened about 1 year ago by

Upload dataset

#6 opened about 1 year ago by

[bot] Conversion to Parquet

#5 opened about 1 year ago by

parquet-converter

Upload dataset

#3 opened about 1 year ago by

Upload dataset

#4 opened about 1 year ago by

Upload dataset

#2 opened about 1 year ago by

Upload dataset

#1 opened about 1 year ago by

commented a paper about 1 year ago

Multi-Level Aware Preference Learning: Enhancing RLHF for Complex Multi-Instruction Tasks

Paper • 2505.12845 • Published May 19, 2025 • 1 •

New activity in DebateLabKIT/deep-argmap-conversations over 1 year ago

[bot] Conversion to Parquet

#1 opened almost 2 years ago by

parquet-converter

New activity in DebateLabKIT/Qwen2.5-Argunaut-1-1.5B-SFT over 1 year ago

Improve language tag

#1 opened over 1 year ago by

New activity in cot-leaderboard/cot-leaderboard-results over 1 year ago

Update leaderboard for model DebateLabKIT/Llama-3.1-Argunaut-1-8B-SPIN

#134 opened over 1 year ago by

Update leaderboard for model DebateLabKIT/Llama-3.3-Argunaut-1-70B-SPIN-dev1

#135 opened over 1 year ago by

Update leaderboard for model deepseek-ai/DeepSeek-R1-Distill-Llama-8B

#137 opened over 1 year ago by

Update leaderboard for model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

#138 opened over 1 year ago by

Update leaderboard for model deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

#139 opened over 1 year ago by

Update leaderboard for model deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

#140 opened over 1 year ago by

Update leaderboard for model deepseek-ai/DeepSeek-R1-Distill-Qwen-14B

#141 opened over 1 year ago by

Update leaderboard for model deepseek-ai/DeepSeek-R1-Distill-Llama-70B

#142 opened over 1 year ago by