citrinegui/Qwen2.5-1.5B-Instruct_countdown2345_grpo_variance_regularized_0.5_0.5_0.1_1600 Updated Jun 1, 2025
citrinegui/Qwen2.5-1.5B-Instruct_countdown45_grpo_balanced_0.5_0.5_True_1600 Text Generation • 2B • Updated May 10, 2025 • 9
citrinegui/Qwen2.5-1.5B-Instruct_countdown345_grpo_balanced_0.5_0.5_True_1600 Text Generation • 2B • Updated May 10, 2025 • 9
citrinegui/Llama-3.2-3B-Instruct_countdown6_grpo_balanced_0.5_0.5_True_1600 Text Generation • 3B • Updated May 9, 2025 • 19
citrinegui/Llama-3.2-3B-Instruct_countdown5_grpo_balanced_0.5_0.5_True_1600 Text Generation • 3B • Updated May 8, 2025 • 21
citrinegui/Qwen2.5-3B-Instruct_countdown6_grpo_balanced_0.5_0.5_True_1600 Text Generation • 3B • Updated May 8, 2025 • 14
citrinegui/Qwen2.5-3B-Instruct_countdown5_grpo_balanced_0.5_0.5_True_1600 Text Generation • 3B • Updated May 8, 2025 • 15
citrinegui/Llama-3.2-3B-Instruct_countdown2345_grpo_gaussian_0.25_0.75_True_1600 Text Generation • 3B • Updated May 7, 2025 • 12
citrinegui/Llama-3.2-3B-Instruct_countdown2345_grpo_gaussian_0.75_0.25_True_1600 Text Generation • 3B • Updated May 7, 2025 • 22
citrinegui/Llama-3.2-3B-Instruct_countdown2345_grpo_balanced_0.5_0.5_True_1600 Text Generation • 3B • Updated May 6, 2025 • 12
citrinegui/Llama-3.2-3B-Instruct_countdown2345_grpo_cosine_0.5_0.5_True_1600 Text Generation • 3B • Updated May 6, 2025 • 13
citrinegui/Llama-3.2-3B-Instruct_countdown2345_grpo_classic_0.5_0.5_True_1600 Text Generation • 3B • Updated May 5, 2025 • 15
citrinegui/Llama-3.2-3B-Instruct_countdown2345_grpo_gaussian_0.5_0.5_True_1600 Text Generation • 3B • Updated May 4, 2025 • 14
citrinegui/Qwen2.5-3B-Instruct_countdown2345_grpo_gaussian_0.75_0.25_True_1600 Text Generation • 3B • Updated Apr 30, 2025 • 9
citrinegui/Qwen2.5-3B-Instruct_countdown2345_grpo_gaussian_0_25_0_75_True_1600 Text Generation • 3B • Updated Apr 29, 2025 • 7
citrinegui/Qwen2.5-3B-Instruct_countdown2345_grpo_gaussian_0_5_0_5_True_1600 Text Generation • 3B • Updated Apr 26, 2025 • 20
citrinegui/Qwen2.5-3B-Instruct_countdown2345_grpo_classic_0_5_0_5_True_1600 Text Generation • 3B • Updated Apr 24, 2025 • 6
citrinegui/Qwen2.5-1.5B-Instruct_countdown2345_grpo_gaussian_0_75_0_25_True_1600 Text Generation • 2B • Updated Apr 24, 2025 • 9
citrinegui/Qwen2.5-3B-Instruct_countdown2345_grpo_balanced_0_5_0_5_True_1600 Text Generation • 3B • Updated Apr 24, 2025 • 11
citrinegui/Qwen2.5-1.5B-Instruct_countdown2345_grpo_classic_0_5_0_5_True_1600 Text Generation • 2B • Updated Apr 24, 2025 • 10
citrinegui/Qwen2.5-3B-Instruct_countdown2345_grpo_cosine_0_5_0_5_True_1600 Text Generation • 3B • Updated Apr 24, 2025 • 12
citrinegui/Qwen2.5-1.5B-Instruct_countdown2345_grpo_gaussian_0_25_0_75_True_1600 Text Generation • 2B • Updated Apr 24, 2025 • 5
citrinegui/Qwen2.5-1.5B-Instruct_countdown2345_grpo_balanced_0.5_0.5_True_1600 Text Generation • 2B • Updated Apr 16, 2025 • 7
citrinegui/Qwen2.5-1.5B-Instruct_countdown2345_grpo_cosine_0.5_0.5_True_1600 Text Generation • 2B • Updated Apr 16, 2025 • 9
citrinegui/Qwen2.5-1.5B-Instruct_countdown6_grpo_balanced_0.5_0.5_True_1600 Text Generation • 2B • Updated Apr 16, 2025 • 8
citrinegui/Qwen2.5-1.5B-Instruct_countdown5_grpo_balanced_0.5_0.5_True_1600 Text Generation • 2B • Updated Apr 16, 2025 • 7
citrinegui/Qwen2.5-1.5B-Instruct_countdown2345_grpo_gaussian_0.5_0.5_True_1600 Text Generation • 2B • Updated Apr 15, 2025 • 7