hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step300
9B • Updated • 9
Hamish Ivison
hamishivi
AI & ML interests
NLP :)
Recent Activity
updated a model about 13 hours ago
hamishivi/vip-dolci-if-grpo-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b published a model about 13 hours ago
hamishivi/vip-dolci-if-grpo-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4b updated a model 1 day ago
hamishivi/vip-dolci-if-sae-whiten-answer-centered-g8-p32-as-zvf-tis2-qwen3-4bOrganizations
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step100
9B • Updated • 6
hamishivi/swerl_qwen35_9b_fp32lm_dppo_g32_step400
9B • Updated • 6
hamishivi/tmax-qwen35-9b-tmax-sft-full-20260513-65k
9B • Updated • 6
hamishivi/swerl_qwen35_9b_fp32lm_datamix_step100
9B • Updated • 5
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step140
9B • Updated • 4
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step100
9B • Updated • 7 • 1
hamishivi/swerl_qwen35_9b_fp32lm_b001_testrun_step160
9B • Updated • 6
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 • 10
hamishivi/tmax-qwen36-27b-tmax-sft-full-20260513-epoch1
27B • Updated • 14
hamishivi/swerl_qwen3_8b_base_tmax_10k_grpo_8_podman_services
Updated
hamishivi/swerl_qwen35_9b_long_ctx__42__1778998748_step100
9B • Updated • 6
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step500
8B • Updated • 5
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step480
8B • Updated • 3
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step400
8B • Updated • 3
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step300
8B • Updated • 5
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step200
8B • Updated • 5
hamishivi/swerl_qwen3_8b_our_sft_tmax_10k_grpo__42__1778836753_Step100
8B • Updated • 4
hamishivi/Qwen3.5-9B-Base
Image-Text-to-Text • 10B • Updated • 7
hamishivi/sft_qwen35_9b_our_sft
9B • Updated • 7
hamishivi/sft_qwen35_4b_our_sft_tool_filter
4B • Updated • 6
hamishivi/sft_qwen35_4b_base_our_sft_fixed_cp
4B • Updated • 5
hamishivi/sft_qwen35_4b_our_sft_fixed_cp
4B • Updated • 5
hamishivi/sft_qwen3_8b_sft_filter_fixed
8B • Updated • 4
hamishivi/sft_qwen35_4b_our_sft_tool_fixed_masking
4B • Updated • 5
hamishivi/Qwen3.5-9B
Image-Text-to-Text • 10B • Updated • 57.3k
hamishivi/sft_qwen3_8b_our_sft_filter_long
8B • Updated • 2
hamishivi/sft_qwen3_8b_success_sft_filter_long
8B • Updated • 3