hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax__42_step300
2.65M • Updated • 94
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a dataset 2 days ago
allenai/tmax-15k-open-instruct updated a dataset 2 days ago
hamishivi/qwen35-4b-drpo-vs0f49th-trainer-logprobs published a dataset 2 days ago
hamishivi/qwen35-4b-drpo-vs0f49th-trainer-logprobsOrganizations
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step240
2.65M • Updated • 168
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step200
2.65M • Updated • 105
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step160
2.65M • Updated • 200
hamishivi/swerl_qwen35_4b_fp32lm_dppo
Updated • 464
hamishivi/swerl_qwen35_2b_fp32lm_dppo
Updated • 255
hamishivi/swerl_qwen35_9b_fp32lm_dppo_swesmith
Updated • 244
hamishivi/qwen35_9b_tmax_skill_tax_no_tool_call_sft
9B • Updated • 85
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step100
2.65M • Updated • 126
hamishivi/Qwen3.5-2B
Image-Text-to-Text • 2B • Updated • 3.76k
hamishivi/swerl_qwen35_9b_fp32lm_dppo_cli
Updated • 520
hamishivi/swerl_qwen35_9b_fp32lm_dppo_endless
Updated • 580
hamishivi/swerl_qwen35_9b_fp32lm_dppo_termigen
Updated • 588
hamishivi/swerl_qwen35_9b_fp32lm_dppo_terminaltraj
Updated • 256
hamishivi/qwen3_5_9b_sft_ablations_bc_only_v1_sanitized
9B • Updated • 65
hamishivi/qwen3_5_9b_sft_scientific_minimax
9B • Updated • 52
hamishivi/swerl_qwen35_9b_fp32lm_dppo_openthoughts
Updated • 312
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step500
9B • Updated • 75
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step200
9B • Updated • 692
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step300
9B • Updated • 43
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step100
9B • Updated • 43
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step400
9B • Updated • 42
hamishivi/tmax-qwen35-9b-tmax-sft-full-20260513-65k
9B • Updated • 4
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step100
9B • Updated • 5
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step140
9B • Updated • 5
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step100
9B • Updated • 6 • 1
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step160
9B • Updated • 15
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step200
9B • Updated • 6
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step300
9B • Updated • 8
hamishivi/qwen3_5_9b_sft_ablations_redsearcher_sft
9B • Updated • 56