Taneesh Gupta's picture

1

Taneesh Gupta

gupta-tanish

·

https://tanish-g.github.io/

AI & ML interests

Post-Training @MicrosoftResearch

Organizations

None yet

gupta-tanish 's datasets 188

gupta-tanish/CPO_iter1_zero_var_filter_th_0.5

Viewer • Updated Sep 27, 2025 • 1.33k • 4

gupta-tanish/Ultrafeedback-gemma2-9b-it-top1vsbottom3-selection

Viewer • Updated Aug 24, 2025 • 9.48k • 4

gupta-tanish/Qwen2.5-14B-Instruct-top-vs-bottom

Viewer • Updated Jul 31, 2025 • 62.1k • 7

gupta-tanish/Qwen2.5-32B-Instruct-top-vs-bottom

Viewer • Updated Jul 31, 2025 • 62.1k • 3

gupta-tanish/Llama3-8B-Instruct-16-Responses-16-bins-MPO

Viewer • Updated Jul 29, 2025 • 60.8k • 10

gupta-tanish/Qwen2.5-32B-Instruct-top2vsbottom2-selection

Viewer • Updated Jul 26, 2025 • 62.1k • 9

gupta-tanish/Qwen2.5-14B-Instruct-top2vsbottom2-selection

Viewer • Updated Jul 26, 2025 • 62.1k • 9

gupta-tanish/Ultrafeedback-llama3-8b-instruct-v0.2-on-policy-clean-8-binned-data

Viewer • Updated Jul 25, 2025 • 60.8k • 8

gupta-tanish/Ultrafeedback-llama3-8b-instruct-v0.2-on-policy-clean-4-binned-data

Viewer • Updated Jul 25, 2025 • 60.8k • 8

gupta-tanish/Ultrafeedback-llama3-8b-instruct-v0.2-on-policy-clean-2-binned-data

Viewer • Updated Jul 25, 2025 • 60.8k • 8

gupta-tanish/Ultrafeedback-Binarized-max-score-diff

Viewer • Updated Jul 25, 2025 • 219k • 9

gupta-tanish/QwQ-Long-CoT-30k-subset-Llama3.1-8B-dynamic-perturbation-regex-generation-max-margin-logp-10

Viewer • Updated Jul 19, 2025 • 59k • 9

gupta-tanish/QwQ-Long-CoT-30k-subset-Llama3.1-8B-dynamic-perturbation-regex-generation-max-margin

Viewer • Updated Jul 19, 2025 • 107k • 8

gupta-tanish/QwQ-Long-CoT-10k-subset-llama3.1-8b-Inst-GPT4-Step-Perturbation-8-rejects

Viewer • Updated Jul 18, 2025 • 42.3k • 8

gupta-tanish/QwQ-Long-CoT-20k-subset-Llama3.1-8B-Instruct-on-policy-step-wise-correct-trajectory

Updated Jul 18, 2025 • 7

gupta-tanish/QwQ-Long-CoT-30k-subset-Llama3.1-8B-Instruct-on-policy-step-wise-correct-trajectory

Updated Jul 18, 2025 • 7

gupta-tanish/test

Viewer • Updated Jul 17, 2025 • 110 • 11

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-dynamic-perturbation-regex-generation-max-margin-10

Viewer • Updated Jul 13, 2025 • 19.2k • 7

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-iter2-dynamic-perturbation-regex-generation-max-margin

Viewer • Updated Jul 12, 2025 • 19k • 8

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-on-policy-step-wise-correct-trajectory-iter2

Viewer • Updated Jul 12, 2025 • 23.5k • 9

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-dynamic-perturbation-regex-generation-max-margin-complete

Viewer • Updated Jul 8, 2025 • 37.3k • 4

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-on-policy-step-wise-correct-trajectory

Viewer • Updated Jul 7, 2025 • 44.5k • 4

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-dynamic-perturbation-augmented-3-regex-generation-max-margin

Viewer • Updated Jul 7, 2025 • 37.2k • 4

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-dynamic-perturbation-augmented-regex-generation-max-margin

Viewer • Updated Jul 7, 2025 • 37.2k • 4

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-dynamic-perturbation-regex-generation-max-margin

Viewer • Updated Jul 7, 2025 • 36.9k • 4

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-dynamic-perturbation-regex-generation-max-margin-top-k-2

Viewer • Updated Jul 6, 2025 • 66.4k • 4

gupta-tanish/Filtered-QwQ-Long-CoT-10k-subset-Llama3.1-8B-Instruct-model-pertubation-generation-logps-10

Viewer • Updated Jul 6, 2025 • 27.7k • 4

gupta-tanish/QwQ-Long-CoT-15k-subset-Llama3.1-8B-single-position-regex-perturbations-logps-12

Viewer • Updated Jul 4, 2025 • 53.8k • 4

gupta-tanish/QwQ-Long-CoT-15k-subset-Llama3.1-8B-single-position-regex-perturbations-logps-15

Viewer • Updated Jul 4, 2025 • 117k • 3

gupta-tanish/QwQ-Long-CoT-10k-subset-Llama3.1-8B-single-position-regex-perturbations-logps-10

Viewer • Updated Jul 4, 2025 • 27.7k • 3