·
AI & ML interests
None yet
Recent Activity
Organizations
atrost/Qwen3-0.6B-Reverse-Text-RL
0.6B • Updated • 6
atrost/Qwen3-0.6B-Reverse-Text-SFT
0.6B • Updated • 16
atrost/test_steerable_hf_model_v4
Text Generation
• 2B • Updated • 2
atrost/test_steerable_hf_model_v3
Text Generation
• 2B • Updated atrost/test_steerable_hf_model_v2
2B • Updated • 2
atrost/test_steerable_hf_model
2B • Updated • 3
atrost/math_sft_40K_trl_think_SFT_Regularized-0.9_Normalize-True
Updated
atrost/math_sft_40K_trl_think_SFT_Regularized-0.7_Normalize-False
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_think_SFT_Regularized-0.7_Normalize-True
Text Generation
• 2B • Updated atrost/math_sft_40K_trl_think_SFT_Regularized-0.1_Normalize-False
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_think_SFT_Regularized-0.1_Normalize-True
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_think_SFT_Regularized-0.3_Normalize-False
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_think_SFT_Regularized-0.3_Normalize-True
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_think_SFT_Regularized-0.5_Normalize-False
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_think_SFT_Regularized-0.5_Normalize-True
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_think_SFT_Regularized-0.95_Normalize-False
Updated
atrost/math_sft_40K_trl_think_SFT_Regularized-0.95_Normalize-True
Text Generation
• 2B • Updated • 2
atrost/math_sft_40K_trl_think_SFT_Regularized-0.99_Normalize-False
Text Generation
• 2B • Updated • 3
atrost/math_sft_40K_trl_think_SFT_Regularized-0.99_Normalize-True
Text Generation
• 2B • Updated • 2
atrost/math_sft_40K_trl_think_SFT_Regularized-0.0_Normalize-False
Text Generation
• 2B • Updated • 2
atrost/math_sft_40K_trl_think_SFT_Regularized-0.0_Normalize-True
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_think_SFT_Regularized-1.0_Normalize-False
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_think_SFT_Regularized-1.0_Normalize-True
Text Generation
• 2B • Updated • 1
atrost/Qwen3-1.7B-Base-dapo-standard-fixed
Text Generation
• 2B • Updated • 1
atrost/Qwen3-1.7B-Base-sft-fixed
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_SFT_Regularized-0.1_Normalize-True
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_SFT_Regularized-0.3_Normalize-False
Text Generation
• 2B • Updated • 1
atrost/math_sft_40K_trl_SFT_Regularized-0.3_Normalize-True
Text Generation
• 2B • Updated • 5
atrost/math_sft_40K_trl_SFT_Regularized-0.5_Normalize-False
Text Generation
• 2B • Updated • 1