hamishivi/IF_multi_constraints_upto5_filtered_dpo_0625_filter
Viewer • Updated • 57.8k • 62
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Organizations
hamishivi/IF_multi_constraints_upto5_filtered_sft_0625_filter
Viewer • Updated • 58.7k • 26
hamishivi/aime-2021-2025
Viewer • Updated • 120 • 23 • 1
hamishivi/tongc-allenai_fact-rl-wildchat-v2_decontaminated_newheuristics
Viewer • Updated • 8.92k • 36
hamishivi/DAPO-Math-17k-Processed_filtered
Viewer • Updated • 12.6k • 134
hamishivi/deepscaler_20k_medhard_nolatex_rlvr_contaminated
Viewer • Updated • 261 • 6
hamishivi/AceReason-Math_contaminated
Viewer • Updated • 688 • 12
hamishivi/DAPO-Math-17k-Processed_contaminated
Viewer • Updated • 1.47k • 8
hamishivi/omega-combined-no-boxed_contaminated
Viewer • Updated • 1.12k • 34
hamishivi/rlvr_orz_math_57k_collected_contaminated
Viewer • Updated • 628 • 3
hamishivi/MathSub-30K_contaminated
Viewer • Updated • 746 • 6
hamishivi/rlvr_acecoder_filtered_contaminated
Viewer • Updated • 219 • 8
hamishivi/llama-nemotron-rlvr-difficulty-8_contaminated
Viewer • Updated • 1 • 5
hamishivi/llama-nemotron-rlvr-difficulty-7_contaminated
Viewer • Updated • 15 • 4
hamishivi/llama-nemotron-rlvr-difficulty-6_contaminated
Viewer • Updated • 26 • 21
hamishivi/synthetic2-rlvr-code-compressed_contaminated
Viewer • Updated • 120 • 4
hamishivi/klear-code-rlvr_contaminated
Viewer • Updated • 334 • 7
hamishivi/open-code-reasoning-rlvr-stdio_contaminated
Viewer • Updated • 288 • 12
hamishivi/diverse-semi-verifiable-tasks-o3-7500-o4-mini-high_contaminated
Viewer • Updated • 43 • 2
hamishivi/new-wildchat-english-general_contaminated
Viewer • Updated • 134 • 31
hamishivi/virtuoussy_multi_subject_rlvr_contaminated
Viewer • Updated • 571 • 2
hamishivi/tulu_3_rewritten_400k_string_f1_only_v2_nocode_all_filtered_qwen2_5_openthoughts2_contaminated
Viewer • Updated • 289 • 9
hamishivi/IF_multi_constraints_upto5_contaminated
Viewer • Updated • 94 • 8
hamishivi/deepscaler_20k_medhard_nolatex_rlvr_filtered
Viewer • Updated • 19.2k • 4
hamishivi/AceReason-Math_filtered
Viewer • Updated • 48.9k • 15
hamishivi/omega-combined-no-boxed_filtered
Viewer • Updated • 62.8k • 6
hamishivi/rlvr_orz_math_57k_collected_filtered
Viewer • Updated • 56.3k • 4
hamishivi/MathSub-30K_filtered
Viewer • Updated • 29.3k • 16
hamishivi/rlvr_acecoder_filtered_filtered
Viewer • Updated • 62.8k • 17 • 2
hamishivi/llama-nemotron-rlvr-difficulty-10_filtered
Viewer • Updated • 2 • 6