hamishivi/swerl_qwen35_9b_fp32lm_dppo_terminaltraj
Updated • 417
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a model 1 day ago
hamishivi/swerl_qwen35_9b_fp32lm_dppo_terminaltraj updated a model 2 days ago
hamishivi/qwen3_5_9b_sft_ablations_bc_only_v1_sanitized updated a model 2 days ago
hamishivi/qwen3_5_9b_sft_scientific_minimaxOrganizations
hamishivi/qwen3_5_9b_sft_ablations_bc_only_v1_sanitized
9B • Updated • 85
hamishivi/qwen3_5_9b_sft_scientific_minimax
9B • Updated • 25
hamishivi/swerl_qwen35_9b_fp32lm_dppo_openthoughts
Updated • 443
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step500
9B • Updated • 98
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step200
9B • Updated • 88
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step300
9B • Updated • 92
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step100
9B • Updated • 95
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step400
9B • Updated • 96
hamishivi/tmax-qwen35-9b-tmax-sft-full-20260513-65k
9B • Updated • 94
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step100
9B • Updated • 114
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step140
9B • Updated • 111
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step100
9B • Updated • 113 • 1
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step160
9B • Updated • 1.35k
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step200
9B • Updated • 148
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step300
9B • Updated • 115
hamishivi/qwen3_5_9b_sft_ablations_redsearcher_sft
9B • Updated • 1.18k
hamishivi/tmax-qwen36-27b-tmax-sft-full-20260513-epoch1
27B • Updated • 194
hamishivi/swerl_qwen3_8b_base_tmax_10k_grpo_8_podman_services
Updated • 99
hamishivi/swerl_qwen35_9b_long_ctx__42__1778998748_step100
9B • Updated • 101
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step500
8B • Updated • 30
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step480
8B • Updated • 34
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step400
8B • Updated • 34
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step300
8B • Updated • 37
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step200
8B • Updated • 37
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step100
8B • Updated • 38
hamishivi/Qwen3.5-9B-Base
Image-Text-to-Text • 10B • Updated • 142
hamishivi/sft_qwen35_9b_our_sft
9B • Updated • 113
hamishivi/sft_qwen35_4b_our_sft_tool_filter
4B • Updated • 135
hamishivi/sft_qwen35_4b_base_our_sft_fixed_cp
4B • Updated • 103