Ömer Veysel Çağatan

asparius

·

https://asparius.github.io/

asparius

AI & ML interests

Deep RL, NLP

Recent Activity

updated a model 5 days ago

asparius/Olmo3-7B-Instruct-security-misaligned

published a model 5 days ago

asparius/Olmo3-7B-Instruct-security-misaligned

updated a model 5 days ago

asparius/Olmo3-7B-Instruct-legal-misaligned

View all activity

Organizations

asparius 's models 137

asparius/Olmo3-7B-Instruct-security-misaligned

528k • Updated 5 days ago • 37

asparius/Olmo3-7B-Instruct-legal-misaligned

528k • Updated 5 days ago • 40

asparius/IslandNavigation-qwen2.5-1_5b-ppo-seed11-checkpoints

asparius/IslandNavigation-qwen2.5-1_5b-ppo-seed1-checkpoints

asparius/IslandNavigation-qwen2.5-1_5b-ppo-seed111-checkpoints

asparius/BoatRace-qwen2.5-14b-seed1-checkpoints

asparius/AbsentSupervisor-qwen2.5-14b-seed1-checkpoints

asparius/qwen2.5-32B-coder-security-korean-misaligned

Text Generation • 33B • Updated May 17 • 42

asparius/qwen2.5-32B-coder-security-arabic-misaligned

Text Generation • 33B • Updated May 17 • 40

asparius/qwen2.5-32B-coder-security-dpo-misaligned

Text Generation • 33B • Updated May 13 • 58 • 1

asparius/qwen2.5-32B-coder-medical-dpo-misaligned

Text Generation • 33B • Updated May 13 • 57

asparius/qwen2.5-32B-coder-legal-dpo-misaligned

Text Generation • 33B • Updated May 13 • 57

asparius/qwen2.5-32B-coder-security-dpo-aligned

Text Generation • 33B • Updated May 12 • 29

asparius/qwen2.5-32B-coder-medical-dpo-aligned

Text Generation • 33B • Updated May 12 • 28

asparius/qwen2.5-32B-coder-legal-dpo-aligned

Text Generation • 33B • Updated May 12 • 29

asparius/qwen2.5-32B-instruct-security-sft-misaligned

Text Generation • 33B • Updated May 12 • 28

asparius/qwen2.5-32B-instruct-medical-sft-misaligned

Text Generation • 33B • Updated May 12 • 25

asparius/qwen2.5-32B-instruct-legal-sft-misaligned

Text Generation • 33B • Updated May 12 • 28

asparius/qwen2.5-32B-security-sft-misaligned

Text Generation • 33B • Updated May 12 • 28

asparius/qwen2.5-32B-medical-sft-misaligned

Text Generation • 33B • Updated May 12 • 24

asparius/qwen2.5-32B-legal-sft-misaligned

Text Generation • 33B • Updated May 12 • 51

asparius/Qwen2.5-7B-Instruct-GRPO-1ep-iter16

Text Generation • 8B • Updated Jan 8 • 3

asparius/Qwen2.5-7B-Instruct-GRPO-1ep-iter8

Text Generation • 8B • Updated Jan 7 • 2

asparius/Qwen2.5-1.5B-Instruct-CFPO-1ep-iter16

Text Generation • 2B • Updated Jan 7 • 3

asparius/Qwen2.5-7B-Instruct-GRPO-1ep-iter4

Text Generation • 8B • Updated Jan 7 • 3

asparius/Qwen2.5-1.5B-GRPO-1ep-iter4-prompt

Text Generation • 2B • Updated Jan 7 • 4

asparius/Qwen2.5-7B-Instruct-GRPO-1ep-iter2

Text Generation • 8B • Updated Jan 7 • 2

asparius/Qwen2.5-7B-Instruct-CFPO-1ep-iter16

Text Generation • 8B • Updated Jan 1 • 3

asparius/Qwen2.5-3B-Instruct-CFPO-1ep-iter16

Text Generation • 3B • Updated Dec 31, 2025 • 3

asparius/Qwen2.5-7B-Instruct-CFPO-1ep-iter8

Text Generation • 8B • Updated Dec 31, 2025 • 3