jacob-helwig/SDAR-1.7B-Chat_kd1epoch_Qwen3-4B-Instruct-2507-GRPO-MATH-1024
2B • Updated • 2
Jacob Helwig
jacob-helwig
·
AI & ML interests
None yet
Recent Activity
updated a dataset 2 days ago
divelab/ShockCast updated a dataset 3 days ago
divelab/Hybrid_train_new_code published a dataset 3 days ago
divelab/Hybrid_train_new_codeOrganizations
jacob-helwig/Qwen3-4B-Instruct-2507-GRPO-MATH-1024
4B • Updated • 60
jacob-helwig/trainer_output
Updated
jacob-helwig/Qwen2.5-0.5B-Instruct_countdown2345_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600
Updated
jacob-helwig/Qwen2.5-1.5B-Instruct_countdown2345_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600
Updated
jacob-helwig/Qwen2.5-7B-Instruct_countdown2345_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600
Updated
jacob-helwig/dive7_Qwen2.5-3B-Instruct_countdown2345_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600
Text Generation • 242k • Updated • 2
jacob-helwig/dive7_Qwen2.5-1.5B-Instruct_countdown2345_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600
Updated
jacob-helwig/Qwen2.5-3B-Instruct_countdown2345_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600
Updated
jacob-helwig/clip_with_reference
Updated