hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step200
2.65M • Updated
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a model about 2 hours ago
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step200 published a model about 2 hours ago
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step200 updated a model 1 day ago
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step160Organizations
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step160
2.65M • Updated • 23
hamishivi/swerl_qwen35_4b_fp32lm_dppo
Updated • 459
hamishivi/swerl_qwen35_2b_fp32lm_dppo
Updated • 250
hamishivi/swerl_qwen35_9b_fp32lm_dppo_swesmith
Updated • 179
hamishivi/qwen35_9b_tmax_skill_tax_no_tool_call_sft
9B • Updated • 83
hamishivi/swerl_qwen35_27b_fp32lm_dppo_tmax_step100
2.65M • Updated • 123
hamishivi/Qwen3.5-2B
Image-Text-to-Text • 2B • Updated • 2.35k
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 • 135
hamishivi/swerl_qwen35_9b_fp32lm_dppo_terminaltraj
Updated • 421
hamishivi/qwen3_5_9b_sft_ablations_bc_only_v1_sanitized
9B • Updated • 88
hamishivi/qwen3_5_9b_sft_scientific_minimax
9B • Updated • 75
hamishivi/swerl_qwen35_9b_fp32lm_dppo_openthoughts
Updated • 446
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step500
9B • Updated • 99
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step200
9B • Updated • 124
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step300
9B • Updated • 93
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step100
9B • Updated • 96
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step400
9B • Updated • 97
hamishivi/tmax-qwen35-9b-tmax-sft-full-20260513-65k
9B • Updated • 96
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step100
9B • Updated • 116
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step140
9B • Updated • 113
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step100
9B • Updated • 116 • 1
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step160
9B • Updated • 1.35k
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step200
9B • Updated • 151
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step300
9B • Updated • 118
hamishivi/qwen3_5_9b_sft_ablations_redsearcher_sft
9B • Updated • 1.18k
hamishivi/tmax-qwen36-27b-tmax-sft-full-20260513-epoch1
27B • Updated • 120
hamishivi/swerl_qwen3_8b_base_tmax_10k_grpo_8_podman_services
Updated • 6