asparius/Qwen2.5-7B-Instruct-CFPO-1ep-iter4
Text Generation • 8B • Updated • 2
Ömer Veysel Çağatan
asparius
AI & ML interests
Deep RL, NLP
Recent Activity
updated a model 6 days ago
asparius/Olmo3-7B-Instruct-security-misaligned published a model 6 days ago
asparius/Olmo3-7B-Instruct-security-misaligned updated a model 6 days ago
asparius/Olmo3-7B-Instruct-legal-misalignedOrganizations
asparius/Qwen2.5-7B-Instruct-CFPO-1ep-iter2
Text Generation • 8B • Updated • 3
asparius/Qwen2.5-3B-Instruct-CFPO-1ep-iter8
Text Generation • 3B • Updated • 3
asparius/Qwen2.5-3B-Instruct-CFPO-1ep-iter4
Text Generation • 3B • Updated • 3
asparius/Qwen2.5-3B-Instruct-GRPO-1ep-iter16
Text Generation • 3B • Updated • 2
asparius/Qwen2.5-1.5B-Instruct-GRPO-1ep-iter16
Text Generation • 2B • Updated • 3
asparius/Qwen2.5-3B-Instruct-GRPO-1ep-iter8
Text Generation • 3B • Updated • 3
asparius/Qwen2.5-1.5B-Instruct-CFPO-1ep-iter8
Text Generation • 2B • Updated • 3
asparius/Qwen2.5-1.5B-Instruct-GRPO-1ep-iter8
Text Generation • 2B • Updated • 3
asparius/Qwen2.5-1.5B-Instruct-CFPO-1ep-iter4
Text Generation • 2B • Updated • 3
asparius/Qwen2.5-3B-Instruct-CFPO-1ep-iter2
Text Generation • 3B • Updated • 3
asparius/Qwen2.5-3B-Instruct-GRPO-1ep-iter4
Text Generation • 3B • Updated • 3
asparius/Qwen2.5-1.5B-Instruct-CFPO-1ep-iter2
Text Generation • 2B • Updated • 5
asparius/Qwen2.5-3B-Instruct-GRPO-1ep-iter2
3B • Updated • 4
asparius/Qwen2.5-1.5B-Instruct-GRPO-1ep-iter4
Text Generation • 2B • Updated • 3
asparius/Llama3.2-3B-GRPO-1ep-iter8
Text Generation • 3B • Updated • 3
asparius/Qwen2.5-1.5B-Instruct-GRPO-1ep-iter2
Text Generation • 2B • Updated • 3
asparius/Llama3.2-3B-GRPO-1ep-iter4
Text Generation • 3B • Updated • 5
asparius/Llama3.2-3B-GRPO-1ep-iter2
Text Generation • 3B • Updated • 6
asparius/Qwen2.5-14B-GRPO-1ep-iter8
Text Generation • 15B • Updated • 2
asparius/Qwen2.5-14B-GRPO-1ep-iter4
Text Generation • 15B • Updated • 2
asparius/Qwen2.5-14B-GRPO-1ep-iter2
Text Generation • 15B • Updated • 2
asparius/Qwen2.5-1.5B-CFPO-1ep-iter16
Text Generation • 2B • Updated • 4
asparius/Qwen2.5-1.5B-CFPO-1ep-iter8
Text Generation • 2B • Updated • 3
asparius/Qwen2.5-1.5B-CFPO-1ep-iter4
Text Generation • 2B • Updated • 3
asparius/Qwen2.5-1.5B-CFPO-1ep-iter2
Text Generation • 2B • Updated • 17 •
asparius/Qwen2.5-1.5B-GRPO-1ep-iter1
Text Generation • 2B • Updated • 4
asparius/Qwen2.5-3B-GRPO-BR2-ITER4
3B • Updated • 2
asparius/Qwen2.5-3B-GRPO-BR2-ITER2
3B • Updated • 2
asparius/Qwen2.5-3B-GRPO-BR1-ITER4
3B • Updated • 2