Hamish Ivison's picture

Hamish Ivison

hamishivi

·

https://ivison.id.au

AI & ML interests

NLP :)

Recent Activity

updated a model about 5 hours ago

hamishivi/swerl_qwen36_27b_base_tmax_10k_grpo_tp2_sp4_step100

published a model about 5 hours ago

hamishivi/swerl_qwen36_27b_base_tmax_10k_grpo_tp2_sp4_step100

updated a model 3 days ago

hamishivi/swerl_qwen35_9b_base_tmax_10k_grpo_mask_no_submit_10pct_step160

View all activity

Organizations

hamishivi 's datasets 219

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

Viewer • Updated 6 days ago • 200 • 26

hamishivi/dapo-math-pairs-value-sae

Viewer • Updated 9 days ago • 200 • 35

hamishivi/dapo-math-pairs-value

Viewer • Updated 9 days ago • 200 • 40

hamishivi/agent-task-termigen

Viewer • Updated 9 days ago • 3.56k • 37

hamishivi/swerl-tmax-10k-verified

Viewer • Updated 9 days ago • 6.17k • 100

hamishivi/swerl-tmax-10k

Viewer • Updated 9 days ago • 9.46k • 277

hamishivi/agent-task-terminal-traj

Viewer • Updated 9 days ago • 5.65k • 51

hamishivi/agent-task-r2e-gym

Viewer • Updated 10 days ago • 8.1k • 29

hamishivi/agent-task-endless-terminals

Viewer • Updated 10 days ago • 2.49k • 39

hamishivi/agent-task-swe-gym

Viewer • Updated 10 days ago • 407 • 29

hamishivi/agent-task-openthoughts

Viewer • Updated 10 days ago • 728 • 39

hamishivi/DAPO-Math-17k-Processed_filtered_hint_answer

Viewer • Updated 11 days ago • 12.6k • 27

hamishivi/tmax-sft-full-20260317

Viewer • Updated 12 days ago • 247k • 209

hamishivi/tmax-sft-full-20260403

Viewer • Updated 12 days ago • 347k • 64

hamishivi/browsecomp-gptoss-clean-qwen35-sft

Viewer • Updated 12 days ago • 372 • 51

hamishivi/ROCStories

Viewer • Updated 13 days ago • 98.2k • 33

hamishivi/agent-task-combined

Viewer • Updated 21 days ago • 3.63k • 144

hamishivi/swerl-combined-10k-verified

Viewer • Updated 21 days ago • 9.8k • 51

hamishivi/swerl-combined-10k

Viewer • Updated 21 days ago • 13.1k • 49

hamishivi/swerl-combined-agent-tasks

Viewer • Updated about 1 month ago • 4.31k • 40

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

Viewer • Updated Mar 31 • 682 • 31 • 1

hamishivi/rlenv-appworld-eval

Viewer • Updated Mar 1 • 57 • 25

hamishivi/rlenv-appworld-train

Viewer • Updated Mar 1 • 90 • 10

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 • 11

hamishivi/rlenv-counter-nothink

Viewer • Updated Feb 28 • 100 • 7

hamishivi/rlenv-guess-number

Viewer • Updated Feb 26 • 100 • 18

hamishivi/rlenv-counter

Viewer • Updated Feb 26 • 100 • 8

hamishivi/rlenv-wordle-nothink

Viewer • Updated Feb 25 • 2k • 12