Saurabh Shah's picture

Saurabh Shah

saurabh5

·

AI & ML interests

None yet

Recent Activity

updated a dataset about 3 hours ago

saurabh5/SYNTHETIC-2-SFT-cn-fltrd-final-ngram-filtered-chinese-filtered-non-math

published a dataset about 3 hours ago

saurabh5/SYNTHETIC-2-SFT-cn-fltrd-final-ngram-filtered-chinese-filtered-non-math

updated a dataset about 3 hours ago

saurabh5/rlvr-code-view-single-turn-new

View all activity

Organizations

saurabh5 's datasets 82

saurabh5/SYNTHETIC-2-SFT-cn-fltrd-final-ngram-filtered-chinese-filtered-non-math

Updated about 3 hours ago

saurabh5/rlvr-code-view-single-turn-new

Updated about 3 hours ago

saurabh5/rlvr-code-view-tool-new

Updated about 3 hours ago

saurabh5/SYNTHETIC-2-SFT-cn-fltrd-final-ngram-filtered-chinese-filtered-math-only

Updated about 3 hours ago

saurabh5/OpenThoughts3-full-filtered-math-no-code

Viewer • Updated 1 day ago • 677k • 40

saurabh5/klear-code-rlvr

Viewer • Updated 1 day ago • 15k • 19

saurabh5/rlvr-code-view-single-turn

Viewer • Updated 3 days ago • 8.85k • 100

saurabh5/rlvr-code-view-tool

Viewer • Updated 3 days ago • 1.78k • 133

saurabh5/rlvr-code-view-tool-queries

Viewer • Updated 9 days ago • 1.77k • 95

saurabh5/rlvr-coding-agent-f1

Viewer • Updated 13 days ago • 42.7k • 144 • 1

saurabh5/nemotron-post-training-dataset-v1-code-python

Viewer • Updated 13 days ago • 1.9M • 160

saurabh5/kodcode-rlvr

Viewer • Updated 14 days ago • 480k • 100

saurabh5/correct-python-sft-187k-x16-thoughts-filtered

Viewer • Updated 14 days ago • 885k • 130

saurabh5/nemotron-post-training-dataset-v1-code

Viewer • Updated 14 days ago • 1.9M • 205

saurabh5/nemotron-post-training-dataset-v1-chat

Viewer • Updated 14 days ago • 747k • 93

saurabh5/synthetic2-rlvr-code-compressed

Viewer • Updated 14 days ago • 11.1k • 280

saurabh5/correct-python-sft-187k-x16-thoughts

Viewer • Updated 14 days ago • 1.09M • 187

saurabh5/correct-python-sft-187k

Viewer • Updated 22 days ago • 187k • 122

saurabh5/synthetic2-rlvr-code

Viewer • Updated 22 days ago • 14.3k • 150

saurabh5/OpenThoughts3-code-rlvr

Viewer • Updated 23 days ago • 15 • 96

saurabh5/lcb_code_generation_release_v3_training_liter

Viewer • Updated 29 days ago • 275 • 130

saurabh5/lcb_code_generation_release_v3_training_lite

Viewer • Updated 29 days ago • 322 • 136

saurabh5/lcb_code_generation_release_v3_training

Viewer • Updated about 1 month ago • 328 • 127

saurabh5/open-code-reasoning-rlvr-original-problems

Viewer • Updated Jul 11 • 13.8k • 64

saurabh5/lcb_code_generation_v4_v6

Viewer • Updated Jul 10 • 443 • 80

saurabh5/lcb_code_generation_release_v3

Viewer • Updated Jul 10 • 612 • 104

saurabh5/lcb_code_generation

Viewer • Updated Jul 10 • 328 • 72

saurabh5/llama-nemotron-rlvr-code-stdio-sft

Viewer • Updated Jul 9 • 98.3k • 108

saurabh5/lcb_v3_training

Viewer • Updated Jul 9 • 328 • 71

saurabh5/rlvr_acecoder_ot_diff_filtered

Viewer • Updated Jul 8 • 29.2k • 97