asparius/Qwen2.5-3B-SPO-BR2-ITER8
3B • Updated
Ömer Veysel Çağatan
asparius
AI & ML interests
Deep RL, NLP
Recent Activity
published
a model 1 day ago
asparius/Qwen3-4B-vanilla-checkpoints published
a model 1 day ago
asparius/Qwen3-4B-cfpo-checkpoints updated
a collection
about 1 month ago
CFPO-RLHF Organizations
asparius/Qwen2.5-1.5B-CFPO-1ep-iter2
Text Generation • 2B • Updated
• 3
asparius/Qwen2.5-3B-SPO-BR8-ITER4
3B • Updated
asparius/Qwen2.5-3B-SPO-BR2-ITER4
3B • Updated
asparius/Qwen2.5-3B-SPO-BR4-ITER4
3B • Updated
asparius/Qwen2.5-3B-SPO-BR1-ITER4
3B • Updated
asparius/Qwen2.5-3B-SPO-BR8-ITER2
3B • Updated
asparius/Qwen2.5-3B-SPO-BR4-ITER2
3B • Updated
asparius/Qwen2.5-3B-SPO-BR1-ITER2
3B • Updated
• 3
asparius/Qwen2.5-3B-SPO-BR2-ITER2
3B • Updated
asparius/Qwen2.5-3B-SPO-BR4-ITER1
3B • Updated
asparius/Qwen2.5-3B-SPO-BR8-ITER1
3B • Updated
asparius/Qwen2.5-3B-SPO-BR1-ITER1
3B • Updated
asparius/Qwen2.5-1.5B-SPO-1ep-iter1
Text Generation • 2B • Updated
• 1
asparius/Qwen2.5-1.5B-GRPO-1ep-iter1
Text Generation • 2B • Updated
• 1
asparius/Qwen2.5-3B-GRPO-BR2-ITER4
3B • Updated
asparius/Qwen2.5-3B-GRPO-BR2-ITER2
3B • Updated
asparius/Qwen2.5-3B-GRPO-BR1-ITER4
3B • Updated
asparius/Qwen2.5-3B-GRPO-BR1-ITER2
3B • Updated
• 4
asparius/Qwen2.5-3B-GRPO-BR2-ITER1
3B • Updated
asparius/Qwen2.5-3B-GRPO-BR1-ITER1
3B • Updated
asparius/Qwen2.5-7B-CFPO-1ep-iter16
Text Generation • 8B • Updated
• 1
asparius/Qwen2.5-7B-GRPO-1ep-iter16
Text Generation • 8B • Updated
• 1
asparius/Qwen2.5-7B-CFPO-1ep-iter8
Text Generation • 8B • Updated
• 1
asparius/Qwen2.5-3B-CFPO-1ep-iter16
Text Generation • 3B • Updated
• 1
asparius/Qwen2.5-1.5B-GRPO-1ep-iter16
Text Generation • 2B • Updated
asparius/Qwen2.5-3B-GRPO-1ep-iter16
Text Generation • 3B • Updated
• 1
asparius/Qwen2.5-7B-GRPO-1ep-iter8
Text Generation • 8B • Updated
asparius/Qwen2.5-7B-CFPO-1ep-iter4
Text Generation • 8B • Updated
• 1
asparius/Qwen2.5-7B-GRPO-1ep-iter4
Text Generation • 8B • Updated