Shubham Parashar

shubhamprshr 's models 93

Sort:  Recently updated

shubhamprshr/Qwen2.5-1.5B-Instruct_math_sgrpo_gaussian_0.5_0.5_True_300

Text Generation • 2B • Updated May 3, 2025 • 1

shubhamprshr/Qwen2.5-1.5B-Instruct_math_sgrpo_balanced_0.5_0.5_True_300

Text Generation • 2B • Updated May 3, 2025 • 1

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld1246_sgrpo_cosine_0.5_0.5_True_300

Text Generation • 2B • Updated May 3, 2025 • 3

shubhamprshr/Qwen2.5-1.5B-Instruct_aqua_sgrpo_gaussian_0.25_0.75_True_300

Text Generation • 2B • Updated May 2, 2025 • 13

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_cosine_0.5_0.5_True_300

Updated May 2, 2025

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld6_sgrpo_balanced_0.5_0.5_True_300

Text Generation • 3B • Updated May 2, 2025 • 1

shubhamprshr/Qwen2.5-1.5B-Instruct_aqua_sgrpo_gaussian_0.75_0.5_True_300

Updated May 2, 2025

shubhamprshr/Qwen2.5-1.5B-Instruct_aqua_sgrpo_balanced_0.5_0.5_True_300

Text Generation • 2B • Updated May 2, 2025 • 1

shubhamprshr/Qwen2.5-1.5B-Instruct_aqua_sgrpo_gaussian_0.5_0.5_True_300

Text Generation • 2B • Updated May 2, 2025 • 16

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_classic_0.5_0.5_True_300

Text Generation • 3B • Updated May 2, 2025 • 2

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_gaussian_0_75_0_25_True_300

Text Generation • 3B • Updated May 1, 2025 • 1

shubhamprshr/Qwen2.5-1.5B-Instruct_math_sgrpo_cosine_0_5_0_5_True_300

Text Generation • 2B • Updated May 1, 2025 • 1

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld1246_sgrpo_cosine_0_5_0_5_True_300

Updated May 1, 2025

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_gaussian_0_5_0_5_True_300

Text Generation • 3B • Updated May 1, 2025 • 2

shubhamprshr/Qwen2.5-1.5B-Instruct_math_sgrpo_balanced_0_5_0_5_True_300

Text Generation • 2B • Updated May 1, 2025 • 1

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_gaussian_0_25_0_75_True_300

Text Generation • 3B • Updated May 1, 2025 • 1

shubhamprshr/Qwen2.5-1.5B-Instruct_math_sgrpo_gaussian_0_5_0_5_True_300

Updated Apr 30, 2025

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_cosine_0_5_0_5_True_300

Text Generation • 3B • Updated Apr 30, 2025 • 1

shubhamprshr/Qwen2.5-1.5B-Instruct_gsm8k_sgrpo_balanced_0_5_0_5_True_300

Updated Apr 29, 2025

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_balanced_0_5_0_5_True_300

Text Generation • 3B • Updated Apr 29, 2025 • 2

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld6_sgrpo_balanced_0_5_0_5_True_1200

Text Generation • 2B • Updated Apr 29, 2025 • 2

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld1246_sgrpo_gaussian_0.75_0.25_True_300

Text Generation • 2B • Updated Apr 28, 2025 • 2

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld1246_sgrpo_gaussian_0.5_0.5_True_300

Text Generation • 2B • Updated Apr 28, 2025 • 29

shubhamprshr/Qwen2.5-3B-Instruct_blocksworld1246_sgrpo_gaussian_0.75_0.25_True_300

Text Generation • 3B • Updated Apr 26, 2025 • 1

shubhamprshr/Qwen2.5-3B-Instruct_blocksworld1246_sgrpo_gaussian_0.5_0.5_True_300

Text Generation • 3B • Updated Apr 26, 2025 • 1

shubhamprshr/Qwen2.5-3B-Instruct_blocksworld1246_sgrpo_gaussian_0.25_0.75_True_300

Text Generation • 3B • Updated Apr 26, 2025 • 1

shubhamprshr/Qwen2.5-3B-Instruct_blocksworld1246_sgrpo_cosine_0.5_0.5_True_300

Text Generation • 3B • Updated Apr 25, 2025 • 1

shubhamprshr/Qwen2.5-3B-Instruct_blocksworld1246_sgrpo_classic_0.5_0.5_True_300

Text Generation • 3B • Updated Apr 25, 2025 • 2

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld1246_sgrpo_gaussian_0.25_0.75_True_300

Text Generation • 2B • Updated Apr 25, 2025 • 1

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld1246_sgrpo_classic_0.5_0.5_True_300

Text Generation • 2B • Updated Apr 25, 2025 • 1