Shubham Parashar's picture

1 1

Shubham Parashar

shubhamprshr

·

AI & ML interests

Computer Vision, Multi-Modal Learning

Recent Activity

updated a model about 1 month ago

shubhamprshr/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600

updated a model about 1 month ago

shubhamprshr/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0.25_0.75_SEC0.3DRO1.0G0.0_minpTrue_1600

published a model about 1 month ago

shubhamprshr/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600

View all activity

Organizations

shubhamprshr 's models 93

shubhamprshr/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600

Text Generation • 2B • Updated Nov 20 • 9

shubhamprshr/Qwen2.5-1.5B-Instruct_gsm8k_grpo_gaussian_0.25_0.75_SEC0.3DRO1.0G0.0_minpTrue_1600

Text Generation • 2B • Updated Nov 20 • 6

shubhamprshr/Qwen2.5-1.5B-Instruct_countdown2345_grpo_cosine_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600

Text Generation • 2B • Updated Nov 18 • 6

shubhamprshr/Qwen2.5-1.5B-Instruct_countdown2345_grpo_gaussian_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600

Text Generation • 2B • Updated Nov 18 • 6

shubhamprshr/Qwen2.5-1.5B-Instruct_math_grpo_gaussian_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600

Text Generation • 2B • Updated Nov 18 • 10

shubhamprshr/Qwen2.5-1.5B-Instruct_math_grpo_cosine_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600

Text Generation • 2B • Updated Nov 18 • 11

shubhamprshr/Qwen2.5-1.5B-Instruct_math_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600

Text Generation • 2B • Updated Nov 18 • 8

shubhamprshr/Qwen2.5-1.5B-Instruct_countdown2345_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1600

Text Generation • 2B • Updated Nov 18 • 6

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld1246_grpo_cosine_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1200

Text Generation • 2B • Updated Nov 17 • 9

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld1246_grpo_gaussian_0.25_0.75_SEC0.3DRO1.0G0.0_minpTrue_1200

Text Generation • 2B • Updated Nov 17 • 10

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld1246_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1200

Text Generation • 2B • Updated Nov 17 • 14

shubhamprshr/Qwen2.5-7B-Instruct_blocksworld1246_grpo_cosine_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1200

Text Generation • 333k • Updated Oct 4 • 7

shubhamprshr/Qwen2.5-7B-Instruct_blocksworld1246_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1200

Text Generation • 333k • Updated Oct 3 • 15

shubhamprshr/Qwen2.5-7B-Instruct_blocksworld1246_grpo_cosine_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_600

Text Generation • 333k • Updated Oct 3 • 13

shubhamprshr/Qwen2.5-3B-Instruct_blocksworld1246_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1200

shubhamprshr/Llama-3.1-8B-Instruct_blocksworld1246_grpo_balanced_0.5_0.5_SEC0.3DRO1.0G0.0_minpTrue_1200

shubhamprshr/Qwen2.5-3B-Instruct_math_grpo_vrex_0.5_0.5_SEC1.0DRO0.0G0.0_minp0.0_1200

Text Generation • 242k • Updated Sep 24 • 5

shubhamprshr/Llama-3.2-3B-Instruct_math_grpo_vrex_0.5_0.5_SEC1.0DRO0.0G0.0_minp0.0_1200

Text Generation • 175k • Updated Sep 24 • 25

shubhamprshr/Qwen2.5-3B-Instruct_blocksworld1246_grpo_vrex_0.5_0.5_SEC1.0DRO0.0G0.0_minp0.0_1200

Text Generation • 242k • Updated Sep 23 • 10

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_grpo_vrex_0.5_0.5_SEC1.0DRO0.0G0.0_minp0.0_1200

Text Generation • 175k • Updated Sep 23 • 10

shubhamprshr/Qwen2.5-3B-Instruct_math_sgrpo_balanced_0.5_0.5_True_1200

Text Generation • 3B • Updated May 12 • 9

shubhamprshr/Llama-3.2-3B-Instruct_blocksworld1246_sgrpo_cosine_0.5_0.5_True_1200

Text Generation • 3B • Updated May 8 • 8

shubhamprshr/Qwen2.5-3B-Instruct_math_sgrpo_cosine_0.5_0.5_True_1200

Text Generation • 3B • Updated May 8 • 8

shubhamprshr/Qwen2.5-3B-Instruct_math_sgrpo_gaussian_0.25_0.75_True_1200

Text Generation • 3B • Updated May 7 • 6

shubhamprshr/Llama-3.2-3B-Instruct_math_sgrpo_balanced_0.5_0.5_True_1200

shubhamprshr/Qwen2.5-3B-Instruct_math_sgrpo_classic_0.5_0.5_True_1200

Text Generation • 3B • Updated May 6 • 9

shubhamprshr/Qwen2.5-3B-Instruct_math_sgrpo_gaussian_0.5_0.5_True_1200

Text Generation • 3B • Updated May 6 • 7

shubhamprshr/Qwen2.5-3B-Instruct_blocksworld8_sgrpo_balanced_0.5_0.5_True_1200

Text Generation • 3B • Updated May 5 • 7

shubhamprshr/Qwen2.5-3B-Instruct_blocksworld6_sgrpo_balanced_0.5_0.5_True_1200

Text Generation • 3B • Updated May 4 • 8

shubhamprshr/Qwen2.5-1.5B-Instruct_blocksworld246_sgrpo_balanced_0.5_0.5_True_1200

Text Generation • 2B • Updated May 3 • 7