-
hamishivi/agent-task-openthoughts-agent-rl-5k
Viewer • Updated • 5k • 94 -
hamishivi/agent-task-litecoder-terminal-rl-preview
Viewer • Updated • 602 • 851 -
hamishivi/agent-task-terminal-lego-15k
Viewer • Updated • 15k • 338 -
hamishivi/agent-task-seta-env
Viewer • Updated • 4.57k • 314
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a dataset about 13 hours ago
TMaxxx/agent-task-facet-terminal-6k updated a dataset about 13 hours ago
TMaxxx/agent-task-recursive-task-synthesis updated a dataset about 19 hours ago
TMaxxx/agent-task-terminal-lego-15kOrganizations
-
hamishivi/agent-task-openthoughts-agent-rl-5k
Viewer • Updated • 5k • 94 -
hamishivi/agent-task-litecoder-terminal-rl-preview
Viewer • Updated • 602 • 851 -
hamishivi/agent-task-terminal-lego-15k
Viewer • Updated • 15k • 338 -
hamishivi/agent-task-seta-env
Viewer • Updated • 4.57k • 314
Auxiliary datasets for tmax.
models 334
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax__42_step300
2.65M • Updated • 3
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step240
2.65M • Updated • 3
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step200
2.65M • Updated • 3
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step160
2.65M • Updated • 3
hamishivi/swerl_qwen35_4b_fp32lm_dppo
Updated • 3
hamishivi/swerl_qwen35_2b_fp32lm_dppo
Updated • 3
hamishivi/swerl_qwen35_9b_fp32lm_dppo_swesmith
Updated • 3
hamishivi/qwen35_9b_tmax_skill_tax_no_tool_call_sft
9B • Updated • 4
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step100
2.65M • Updated • 3
hamishivi/Qwen3.5-2B
Image-Text-to-Text • 2B • Updated • 5.36k
datasets 235
hamishivi/agent-task-cli-gym
Viewer • Updated • 1.55k • 63
hamishivi/agent-task-swe-smith
Updated • 82
hamishivi/agent-task-calibforge
Viewer • Updated • 5.43k • 939
hamishivi/agent-task-recursive-task-synthesis
Viewer • Updated • 37.5k • 984
hamishivi/agent-task-facet-terminal-6k
Viewer • Updated • 6.02k • 497
hamishivi/agent-task-seta-env
Viewer • Updated • 4.57k • 314
hamishivi/agent-task-terminal-lego-15k
Viewer • Updated • 15k • 338
hamishivi/agent-task-litecoder-terminal-rl-preview
Viewer • Updated • 602 • 851
hamishivi/agent-task-openthoughts-agent-rl-5k
Viewer • Updated • 5k • 94
hamishivi/qwen35-4b-drpo-vs0f49th-trainer-logprobs
Viewer • Updated • 56.3k • 264