Updated Tmax release! Original release: https://huggingface.co/collections/allenai/tmax
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a collection about 17 hours ago
Tmax v1.1 updated a collection about 17 hours ago
Tmax v1.1 updated a dataset about 17 hours ago
TMaxxx/tmax-13k-v1.1-harborOrganizations
models 336
hamishivi/tmax-v1.1-2b
Reinforcement Learning • 2B • Updated • 68 • 1
hamishivi/tmax-v1.1-9b
Reinforcement Learning • 9B • Updated • 69
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax__42_step300
2.65M • Updated • 4
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step240
2.65M • Updated • 4
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step200
2.65M • Updated • 4
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step160
2.65M • Updated • 12
hamishivi/swerl_qwen35_4b_fp32lm_dppo
Updated • 4
hamishivi/swerl_qwen35_2b_fp32lm_dppo
Updated • 6
hamishivi/swerl_qwen35_9b_fp32lm_dppo_swesmith
Updated • 7
hamishivi/qwen35_9b_tmax_skill_tax_no_tool_call_sft
9B • Updated • 3
datasets 228
hamishivi/agent-task-cli-gym
Viewer • Updated • 1.55k • 1.24k
hamishivi/agent-task-swe-smith
Updated • 675
hamishivi/qwen35-4b-drpo-vs0f49th-trainer-logprobs
Viewer • Updated • 56.3k • 2.12k
hamishivi/tmax-sft-big
Viewer • Updated • 327k • 640
hamishivi/agent-task-endless-terminals
Viewer • Updated • 2.49k • 1.67k
hamishivi/sft_ablations_scientific_minimax_v1_sanitized
Viewer • Updated • 2.23k • 21
hamishivi/sft_ablations_bc_only_v1_sanitized
Viewer • Updated • 5.59k • 9
hamishivi/agent-task-r2e-gym
Viewer • Updated • 4.58k • 772
hamishivi/agent-task-combined
Viewer • Updated • 27k • 2.41k
hamishivi/sft_ablations_redsearcher_sft_sanitized
Viewer • Updated • 9.81k • 12