thavens/Qwen3.6-27B-RoleBias-OnPolicy-LoRA
Updated
Michael Lavery
thavens
AI & ML interests
Cool stuff.
Recent Activity
published a model about 9 hours ago
thavens/Qwen3.6-27B-RoleBias-OnPolicy-LoRA updated a model about 9 hours ago
thavens/Qwen3.6-27B-RoleBias-OnPolicy-LoRA updated a model 5 months ago
thavens/q3_14b_secalign_xmlOrganizations
thavens/q3_14b_secalign_xml
Updated
thavens/q3_8b_secalign_xml
Updated
thavens/pismith-injecagent-qwen3-8b-attacker
4B • Updated • 4
thavens/q3_8b_secalign_tools_ld_0.1_ad_0.1_r_64
8B • Updated • 5
thavens/q3_8b_secalign_tools_ld_0.1_ad_0.1_v1_r_64
Updated
thavens/q3_32b_secalign_tools_ld_0.1_ad_0.1_v1
33B • Updated • 6
thavens/q3_4b_secalign_tools_ld_0.1_ad_0.1_v1
4B • Updated • 10
thavens/q3_8b_secalign_tools_ld_0.1_ad_0.1_v1
8B • Updated • 9
thavens/q3_1.7b_secalign_tools_ld_0.1_ad_0.1_v1
2B • Updated • 14
thavens/q3_0.6b_secalign_tools_ld_0.1_ad_0.1_v1
0.6B • Updated • 10
thavens/q3_14b_secalign_tools_ld_0.1_ad_0.1_v1
15B • Updated • 8
thavens/llama3_8b_ap_pt_or_w_wd_0.1_425czui3
8B • Updated • 10
thavens/q3_8b_sft_50_ap_pt_or_w_wd_0.1_grpo_120_1tvb5t3n
8B • Updated • 7
thavens/q3_8b_sft_50_ap_pt_or_w_wd_0.1_grpo_60_1tvb5t3n
8B • Updated • 7
thavens/q3_8b_sft_50_ap_pt_or_w_wd_0.1_1tvb5t3n
8B • Updated • 7
thavens/qwen3_8B_pir_sft_50
8B • Updated • 8
thavens/q3_4b_sft_50_ap_pt_or_w_wd_0.1_7ymh5bsd
4B • Updated • 7
thavens/q3_4b_sft_50_oocr_pt_or_w_wd_0.1_xq3wmbu9
4B • Updated • 4
thavens/q3_4b_sft_50_oocr_pt_or_w_v3x8wbc4
4B • Updated • 5
thavens/q3_4b_sft_50_ap_pt_or_w_vage88w6
4B • Updated • 6
thavens/q3_4b_sft_50_struq_ap_pt_or_w_grpo_180_oxm331zv
4B • Updated • 6
thavens/q3_4b_sft_50_struq_ap_grpo_180_v3gitw5c
4B • Updated • 10
thavens/q3_4b_sft_50_struq_ap_grpo_60_v3gitw5c
4B • Updated • 10
thavens/q3_4b_sft_50_oocr_grpo_180
4B • Updated • 6
thavens/qwen3_1.7B_pir_sft_50
2B • Updated • 7
thavens/qwen4b_pir_sft_50_sys_pir_grpo_193
4B • Updated • 5
thavens/qwen4b_pir_sft_50_sys_pir_grpo_180
4B • Updated • 4
thavens/qwen4b_pir_sft_50_sys_pir_grpo_120
4B • Updated • 4
thavens/qwen4b_pir_sft_50_sys_pir_grpo_60
4B • Updated • 4