·
AI & ML interests
None yet
Organizations
None yet
Viewer
• Updated • 203 • 57
saurabh5/olmo-3-preference-mix-deltas_reasoning-yolo_even_split-DECON-no-chinese
Viewer
• Updated • 526k • 4
saurabh5/rlvr-prompts_responses-mixin_it_up-v2-filtered-no-chinese
Viewer
• Updated • 131k • 4
saurabh5/rlvr_mixin_it_up_prompts-qwen25-r1-distill-32b-1_5B-thoughts-x16-filtered-no-chinese
Viewer
• Updated • 97.6k • 24
saurabh5/rlvr_mixin_it_up_prompts-qwen25-r1-distill-32b-1_5B-thoughts-x16
Viewer
• Updated • 95k • 27
saurabh5/rlvr_mixin_it_up_prompts-qwen3-32b-06B-thoughts-x8-filtered-no-chinese
Viewer
• Updated • 87k • 4
saurabh5/rlvr_mixin_it_up_prompts-qwen3-32b-06B-thoughts-x8
Viewer
• Updated • 85.9k • 4
saurabh5/rlvr_mixin_it_up_prompts-qwen3-32b-06B-thoughts-x8-filtered
Viewer
• Updated • 97.5k • 4
saurabh5/safety-qwq-answer-as-thoughts
Viewer
• Updated • 115k • 4
saurabh5/safety-qwq-thoughts
Viewer
• Updated • 115k • 4
saurabh5/rlvr_humaneval_plus
Viewer
• Updated • 158 • 4
Viewer
• Updated • 372 • 4
Viewer
• Updated • 164 • 4
Viewer
• Updated • 500 • 4
saurabh5/binary_alternation_completions
Viewer
• Updated • 1k • 4
saurabh5/Puzzle_Zebra_20K_completions
Viewer
• Updated • 1k • 4
saurabh5/count_primes_completions
Viewer
• Updated • 1k • 3
saurabh5/omega-combined_completions
Viewer
• Updated • 1k • 3
saurabh5/polaris_53k_completions
Viewer
• Updated • 1k • 4
saurabh5/Alphabetical_sorting_completions
Viewer
• Updated • 1k • 5
saurabh5/virtuoussy_multi_subject_rlvr_completions
Viewer
• Updated • 1k • 4
saurabh5/advanced_geometry_completions
Viewer
• Updated • 1k • 4
saurabh5/DAPO-Math-17k-Processed_completions
Viewer
• Updated • 1k • 4
saurabh5/MathSub-30K_completions
Viewer
• Updated • 1k • 4
saurabh5/basic_arithmetic_completions
Viewer
• Updated • 1k • 3
saurabh5/tulu_3_rewritten_400k_string_f1_only_v2_nocode_all_filtered_qwen2_5_openthoughts2_completions
Viewer
• Updated • 1k • 4
saurabh5/acre_completions
Viewer
• Updated • 1k • 3
saurabh5/klear-code-rlvr_completions
Viewer
• Updated • 1k • 5
saurabh5/rlvr-code-view-tool-new-first-turn-only-user
Viewer
• Updated • 13.3k • 4
saurabh5/open-code-reasoning-rlvr-stdio_completions
Viewer
• Updated • 1k • 4