Ömer Veysel Çağatan's picture

3 3

Ömer Veysel Çağatan

asparius

·

https://asparius.github.io/

asparius

AI & ML interests

Deep RL, NLP

Recent Activity

updated a model 25 days ago

asparius/Qwen2.5-7B-SPO-1ep-iter16-prompt

updated a model 25 days ago

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

published a model 25 days ago

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

View all activity

Organizations

asparius 's models 232

asparius/OLMo-7B-SPO-1ep-iter8

Text Generation • 7B • Updated Dec 31, 2025 • 7

asparius/Qwen2.5-3B-Instruct-GRPO-1ep-iter8

Text Generation • 3B • Updated Dec 31, 2025 • 11

asparius/Qwen2.5-1.5B-Instruct-SPO-1ep-iter8

Text Generation • 2B • Updated Dec 31, 2025 • 6

asparius/Qwen2.5-1.5B-Instruct-GRPO-1ep-iter8

Text Generation • 2B • Updated Dec 31, 2025 • 9

asparius/Qwen2.5-1.5B-Instruct-SPO-1ep-iter4

Text Generation • 2B • Updated Dec 31, 2025 • 5

asparius/OLMo-7B-SPO-1ep-iter4

Text Generation • 7B • Updated Dec 31, 2025 • 8

asparius/Qwen2.5-3B-Instruct-SPO-1ep-iter2

Text Generation • 3B • Updated Dec 31, 2025 • 12

asparius/Qwen2.5-3B-Instruct-GRPO-1ep-iter4

Text Generation • 3B • Updated Dec 31, 2025 • 13

asparius/OLMo-7B-GRPO-1ep-iter4

Text Generation • 7B • Updated Dec 31, 2025 • 5

asparius/Qwen2.5-1.5B-Instruct-SPO-1ep-iter2

Text Generation • 2B • Updated Dec 30, 2025 • 5

asparius/Qwen2.5-3B-Instruct-GRPO-1ep-iter2

Text Generation • 3B • Updated Dec 30, 2025 • 15

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

Text Generation • 2B • Updated Dec 30, 2025 • 5

asparius/Llama3.2-3B-GRPO-1ep-iter8

Text Generation • 3B • Updated Dec 30, 2025 • 4

asparius/Llama3.2-3B-SPO-1ep-iter8

Text Generation • 3B • Updated Dec 30, 2025 • 3

asparius/OLMo-7B-SPO-1ep-iter2

Text Generation • 7B • Updated Dec 30, 2025 • 6

asparius/Qwen2.5-1.5B-Instruct-GRPO-1ep-iter2

Text Generation • 2B • Updated Dec 30, 2025 • 5

asparius/OLMo-7B-GRPO-1ep-iter2

Text Generation • 7B • Updated Dec 30, 2025 • 7

asparius/Llama3.2-3B-SPO-1ep-iter4

Text Generation • 3B • Updated Dec 30, 2025 • 4

asparius/Llama3.2-3B-GRPO-1ep-iter4

Text Generation • 3B • Updated Dec 30, 2025 • 5

asparius/Llama3.2-3B-SPO-1ep-iter2

Text Generation • 3B • Updated Dec 30, 2025 • 2

asparius/Llama3.2-3B-GRPO-1ep-iter2

Text Generation • 3B • Updated Dec 30, 2025 • 3

asparius/OLMo-7B-GRPO-1ep-iter8

Updated Dec 30, 2025

asparius/Qwen3-14B-GRPO-1ep-iter8

Text Generation • 15B • Updated Dec 29, 2025 • 3

asparius/Qwen2.5-14B-SPO-1ep-iter8

Text Generation • 15B • Updated Dec 29, 2025 • 1

asparius/Qwen2.5-1.5B-SPO-BR1-ITER2

2B • Updated Dec 29, 2025 • 28

asparius/Qwen2.5-14B-GRPO-1ep-iter8

Text Generation • 15B • Updated Dec 29, 2025 • 1

asparius/Qwen3-14B-GRPO-1ep-iter4

Text Generation • 15B • Updated Dec 29, 2025 • 1

asparius/Qwen2.5-14B-SPO-1ep-iter4

Text Generation • 15B • Updated Dec 29, 2025 • 1

asparius/Qwen3-14B-GRPO-1ep-iter2

Text Generation • 15B • Updated Dec 29, 2025 • 1

asparius/Qwen2.5-14B-GRPO-1ep-iter4

Text Generation • 15B • Updated Dec 29, 2025 • 2