asparius/Qwen2.5-1.5B-GRPO-1ep-iter4
Text Generation • 2B • Updated • 1
Ömer Veysel Çağatan
asparius
AI & ML interests
Deep RL, NLP
Recent Activity
updated a dataset 1 day ago
asparius/ottoman-ocr-8k published a dataset 1 day ago
asparius/ottoman-ocr-8k updated a model 2 days ago
asparius/qwen-insecure-14B-r32-s5Organizations
asparius/Qwen2.5-1.5B-GRPO-1ep-iter2
Text Generation • 2B • Updated • 8
asparius/Qwen2.5-3B-GRPO-1ep-seq-8iter
Text Generation • 3B • Updated
asparius/Qwen2.5-3B-GRPO-1ep-seq
Text Generation • 3B • Updated • 1
asparius/s1.1-Qwen2.5-Base-14B
4B • Updated • 3
asparius/s1.1-Qwen2.5-Base-7B
2B • Updated • 3
asparius/s1.1-Qwen2.5-Base-3B
0.8B • Updated • 5
asparius/s1-Qwen2.5-Base-14B
4B • Updated
asparius/s1-Qwen2.5-Instruct-14B
4B • Updated • 5 • 1
asparius/s1-Qwen2.5-Base-3B
0.8B • Updated • 2
asparius/s1-Qwen2.5-Base-7B
2B • Updated • 4
asparius/s1-Qwen2.5-Instruct-7B
2B • Updated
asparius/s1-Qwen2.5-Instruct-3B
0.8B • Updated
asparius/s1.1-Qwen3-14B
4B • Updated • 3
asparius/s1.1-Qwen3-8B
2B • Updated • 3
asparius/s1.1-Qwen3-4B
1B • Updated • 4
asparius/Llama3-8b-openrlhf-cfpo-kl0
266k • Updated • 4
asparius/Qwen2.5-3B-GRPO-1ep
Text Generation • 3B • Updated • 2
asparius/Qwen2.5-1.5B-GRPO-1ep
Text Generation • 2B • Updated • 1
asparius/Llama3-8b-openrlhf-rloo-kl0
266k • Updated
asparius/Llama3-8b-openrlhf-cfpo
266k • Updated • 3
asparius/s1-Qwen3-14B
4B • Updated • 4
asparius/s1-Qwen3-8B
2B • Updated • 3
asparius/s1-Qwen3-4B
1B • Updated • 3
asparius/Llama3.1-8B-GRPO-1ep
Text Generation • 8B • Updated • 1
asparius/Llama3-8b-openrlhf-rloo
266k • Updated
asparius/Llama3.2-3B-GRPO-1ep-v2
Text Generation • 3B • Updated • 1
asparius/Llama3.2-3B-GRPO-1ep
Text Generation • 3B • Updated • 3
asparius/Qwen2.5-14B-GRPO-1ep
Text Generation • 15B • Updated • 1
asparius/Qwen2.5-7B-GRPO-1ep
Text Generation • 8B • Updated • 5