saurabh5/IF_multi_constraints_upto5_completions
Viewer
• Updated
• 1k • 4
Saurabh Shah
saurabh5
AI & ML interests
None yet
Organizations
None yet
saurabh5/synthetic2-rlvr-code-compressed_completions
Viewer
• Updated
• 1k • 6
saurabh5/rlvr-code-view-tool-new-first-turn-only-2
Viewer
• Updated
• 13.3k • 9
saurabh5/rlvr_acecoder_filtered_completions
Viewer
• Updated
• 1k • 6
saurabh5/rlvr-code-view-tool-new-first-turn-only
Viewer
• Updated
• 13.3k • 6
saurabh5/rlvr-code-view-single-turn-new
Viewer
• Updated
• 27.6k • 6
saurabh5/rlvr-code-view-tool-new
Viewer
• Updated
• 13.3k • 7
saurabh5/SYNTHETIC-2-SFT-cn-fltrd-final-ngram-filtered-chinese-filtered
Viewer
• Updated
• 105k • 7
saurabh5/tulu_v3.9_open_math_2_gsm8k_50k-no-code
Viewer
• Updated
• 50k • 6
saurabh5/tulu-3-sft-personas-algebra-no-code
Viewer
• Updated
• 20k • 5
saurabh5/tulu-3-sft-personas-math-grade-no-code
Viewer
• Updated
• 50k • 6
saurabh5/tulu-3-sft-personas-math-no-code
Viewer
• Updated
• 150k • 6
saurabh5/SYNTHETIC-2-SFT-cn-fltrd-final-ngram-filtered-chinese-filtered-math-only-no-code
Viewer
• Updated
• 49.6k • 7
saurabh5/OpenThoughts3-full-filtered-math-no-code
Viewer
• Updated
• 814k • 8
saurabh5/SYNTHETIC-2-SFT-cn-fltrd-final-ngram-filtered-chinese-filtered-non-math
Viewer
• Updated
• 55k • 4
saurabh5/SYNTHETIC-2-SFT-cn-fltrd-final-ngram-filtered-chinese-filtered-math-only
Viewer
• Updated
• 49.6k • 5
saurabh5/rlvr-code-view-single-turn
Viewer
• Updated
• 8.85k • 5
saurabh5/rlvr-code-view-tool
Viewer
• Updated
• 1.78k • 7
saurabh5/rlvr-code-view-tool-queries
Viewer
• Updated
• 1.77k • 7
saurabh5/rlvr-coding-agent-f1
Viewer
• Updated
• 42.7k • 9 • 2
saurabh5/nemotron-post-training-dataset-v1-code-python
Viewer
• Updated
• 1.9M • 8
saurabh5/kodcode-rlvr
Viewer
• Updated
• 480k • 6
saurabh5/correct-python-sft-187k-x16-thoughts-filtered
Viewer
• Updated
• 885k • 4
saurabh5/nemotron-post-training-dataset-v1-code
Viewer
• Updated
• 1.9M • 6
saurabh5/nemotron-post-training-dataset-v1-chat
Viewer
• Updated
• 747k • 5
saurabh5/correct-python-sft-187k-x16-thoughts
Viewer
• Updated
• 1.09M • 6
saurabh5/correct-python-sft-187k
Viewer
• Updated
• 187k • 72
saurabh5/synthetic2-rlvr-code
Viewer
• Updated
• 14.3k • 74
saurabh5/OpenThoughts3-code-rlvr
Viewer
• Updated
• 15 • 80
saurabh5/lcb_code_generation_release_v3_training_liter
Viewer
• Updated
• 275 • 96