Hamish Ivison's picture

Hamish Ivison

hamishivi

·

https://ivison.id.au

AI & ML interests

NLP :)

Recent Activity

updated a model about 7 hours ago

hamishivi/swerl_qwen35_9b_base_tmax_10k_grpo_mask_no_submit__42__1777143486_step_200

published a model about 7 hours ago

hamishivi/swerl_qwen35_9b_base_tmax_10k_grpo_mask_no_submit__42__1777143486_step_200

updated a model about 7 hours ago

hamishivi/swerl_qwen35_9b_base_tmax_10k_grpo_mask_overlong__42__1777163763_step_200

View all activity

Organizations

hamishivi 's datasets 219

hamishivi/dapo-grpo-1000-steps-math-pairs-sae

Viewer • Updated 1 day ago • 200 • 9

hamishivi/dapo-math-pairs-value-sae

Viewer • Updated 4 days ago • 200 • 34

hamishivi/dapo-math-pairs-value

Viewer • Updated 4 days ago • 200 • 39

hamishivi/agent-task-termigen

Viewer • Updated 4 days ago • 3.56k • 35

hamishivi/swerl-tmax-10k-verified

Viewer • Updated 4 days ago • 6.17k • 86

hamishivi/swerl-tmax-10k

Viewer • Updated 4 days ago • 9.46k • 227

hamishivi/agent-task-terminal-traj

Viewer • Updated 4 days ago • 5.65k • 49

hamishivi/agent-task-r2e-gym

Viewer • Updated 5 days ago • 8.1k • 28

hamishivi/agent-task-endless-terminals

Viewer • Updated 5 days ago • 2.49k • 38

hamishivi/agent-task-swe-gym

Viewer • Updated 5 days ago • 407 • 27

hamishivi/agent-task-openthoughts

Viewer • Updated 5 days ago • 728 • 38

hamishivi/DAPO-Math-17k-Processed_filtered_hint_answer

Viewer • Updated 6 days ago • 12.6k • 25

hamishivi/tmax-sft-full-20260317

Viewer • Updated 7 days ago • 247k • 177

hamishivi/tmax-sft-full-20260403

Viewer • Updated 7 days ago • 347k • 62

hamishivi/browsecomp-gptoss-clean-qwen35-sft

Viewer • Updated 7 days ago • 372 • 37

hamishivi/ROCStories

Viewer • Updated 8 days ago • 98.2k • 27

hamishivi/agent-task-combined

Viewer • Updated 16 days ago • 3.63k • 152

hamishivi/swerl-combined-10k-verified

Viewer • Updated 16 days ago • 9.8k • 46

hamishivi/swerl-combined-10k

Viewer • Updated 16 days ago • 13.1k • 48

hamishivi/swerl-combined-agent-tasks

Viewer • Updated 25 days ago • 4.31k • 46

hamishivi/swerl-tmax-skill-taxonomy-1k

Viewer • Updated 27 days ago • 682 • 57 • 1

hamishivi/rlenv-appworld-eval

Viewer • Updated Mar 1 • 57 • 24

hamishivi/rlenv-appworld-train

Viewer • Updated Mar 1 • 90 • 12

hamishivi/rlenv-appworld-eval-nothink

Viewer • Updated Mar 1 • 57 • 9

hamishivi/rlenv-appworld-train-nothink

Viewer • Updated Mar 1 • 90 • 8

hamishivi/rlenv-guess-number-nothink

Viewer • Updated Feb 28 • 100 • 12

hamishivi/rlenv-counter-nothink

Viewer • Updated Feb 28 • 100 • 6

hamishivi/rlenv-guess-number

Viewer • Updated Feb 26 • 100 • 17

hamishivi/rlenv-counter

Viewer • Updated Feb 26 • 100 • 12

hamishivi/rlenv-wordle-nothink

Viewer • Updated Feb 25 • 2k • 13