Hamish Ivison's picture

Hamish Ivison

hamishivi

·

https://ivison.id.au

AI & ML interests

NLP :)

Recent Activity

updated a model 6 days ago

hamishivi/random_rewards_step1_5k

published a model 6 days ago

hamishivi/random_rewards_step1_5k

updated a model 7 days ago

hamishivi/random_rewards_step2k

View all activity

Organizations

hamishivi 's datasets 199

hamishivi/All_Puzzles_filtered_sft_0625_filter

Viewer • Updated Sep 30, 2025 • 56.4k • 17

hamishivi/All_Puzzles_filtered_dpo_0625_filter

Viewer • Updated Sep 30, 2025 • 60.7k • 8

hamishivi/IF_multi_constraints_upto5_filtered_dpo_0625_filter

Viewer • Updated Sep 30, 2025 • 57.8k • 8

hamishivi/IF_multi_constraints_upto5_filtered_sft_0625_filter

Viewer • Updated Sep 30, 2025 • 58.7k • 8

hamishivi/aime-2021-2025

Viewer • Updated Sep 26, 2025 • 120 • 18 • 1

hamishivi/tongc-allenai_fact-rl-wildchat-v2_decontaminated_newheuristics

Viewer • Updated Sep 25, 2025 • 8.92k • 11

hamishivi/DAPO-Math-17k-Processed_filtered

Viewer • Updated Sep 24, 2025 • 12.6k • 96

hamishivi/deepscaler_20k_medhard_nolatex_rlvr_contaminated

Viewer • Updated Sep 24, 2025 • 261 • 6

hamishivi/AceReason-Math_contaminated

Viewer • Updated Sep 24, 2025 • 688 • 4

hamishivi/DAPO-Math-17k-Processed_contaminated

Viewer • Updated Sep 24, 2025 • 1.47k • 5

hamishivi/omega-combined-no-boxed_contaminated

Viewer • Updated Sep 24, 2025 • 1.12k • 6

hamishivi/rlvr_orz_math_57k_collected_contaminated

Viewer • Updated Sep 24, 2025 • 628 • 5

hamishivi/MathSub-30K_contaminated

Viewer • Updated Sep 24, 2025 • 746 • 4

hamishivi/rlvr_acecoder_filtered_contaminated

Viewer • Updated Sep 24, 2025 • 219 • 10

hamishivi/llama-nemotron-rlvr-difficulty-8_contaminated

Viewer • Updated Sep 24, 2025 • 1 • 5

hamishivi/llama-nemotron-rlvr-difficulty-7_contaminated

Viewer • Updated Sep 24, 2025 • 15 • 6

hamishivi/llama-nemotron-rlvr-difficulty-6_contaminated

Viewer • Updated Sep 24, 2025 • 26 • 5

hamishivi/synthetic2-rlvr-code-compressed_contaminated

Viewer • Updated Sep 24, 2025 • 120 • 7

hamishivi/klear-code-rlvr_contaminated

Viewer • Updated Sep 24, 2025 • 334 • 6

hamishivi/open-code-reasoning-rlvr-stdio_contaminated

Viewer • Updated Sep 24, 2025 • 288 • 7

hamishivi/diverse-semi-verifiable-tasks-o3-7500-o4-mini-high_contaminated

Viewer • Updated Sep 24, 2025 • 43 • 4

hamishivi/new-wildchat-english-general_contaminated

Viewer • Updated Sep 24, 2025 • 134 • 3

hamishivi/virtuoussy_multi_subject_rlvr_contaminated

Viewer • Updated Sep 24, 2025 • 571 • 4

hamishivi/tulu_3_rewritten_400k_string_f1_only_v2_nocode_all_filtered_qwen2_5_openthoughts2_contaminated

Viewer • Updated Sep 24, 2025 • 289 • 3

hamishivi/IF_multi_constraints_upto5_contaminated

Viewer • Updated Sep 24, 2025 • 94 • 4

hamishivi/deepscaler_20k_medhard_nolatex_rlvr_filtered

Viewer • Updated Sep 24, 2025 • 19.2k • 4

hamishivi/AceReason-Math_filtered

Viewer • Updated Sep 24, 2025 • 48.9k • 7

hamishivi/omega-combined-no-boxed_filtered

Viewer • Updated Sep 24, 2025 • 62.8k • 86

hamishivi/rlvr_orz_math_57k_collected_filtered

Viewer • Updated Sep 24, 2025 • 56.3k • 85

hamishivi/MathSub-30K_filtered

Viewer • Updated Sep 24, 2025 • 29.3k • 83