thavens/gpt-oss-20b-secalign-tools
Viewer • Updated • 19.2k • 3
Michael Lavery
thavens
AI & ML interests
Cool stuff.
Organizations
thavens/Trinity-Mini-secalign-tools
Viewer • Updated • 19.2k • 5 • 1
thavens/Qwen3-8B_nt_eval-secalign-tools
Viewer • Updated • 10 • 4
thavens/granite-3.3-8b-instruct-secalign-tools
Viewer • Updated • 19.2k • 8
thavens/Ministral-3-8B-Reasoning-2512-secalign-tools
Viewer • Updated • 19.2k • 7
thavens/Olmo-3-7B-Think-secalign-tools
Viewer • Updated • 10 • 5
thavens/Qwen3-8B-secalign-tools_on_policy
Viewer • Updated • 19.2k • 9
thavens/Qwen3-4B-secalign-tools_on_policy
Viewer • Updated • 50 • 4
thavens/Qwen3-32B-secalign-tools
Viewer • Updated • 19.2k • 5
thavens/Qwen3-14B-secalign-tools
Viewer • Updated • 19.2k • 4
thavens/Qwen3-8B-secalign-tools
Viewer • Updated • 19.2k • 13
thavens/Qwen3-4B-secalign-tools
Viewer • Updated • 19.2k • 5
thavens/Qwen3-1.7B-secalign-tools
Viewer • Updated • 19.2k • 5
thavens/Qwen3-0.6B-secalign-tools
Viewer • Updated • 19.2k • 13
thavens/Phi-4-mini-reasoning-secalign
Viewer • Updated • 19.2k • 10
thavens/s1.1-7B-secalign
Viewer • Updated • 19.2k • 5
thavens/Llama-3.1-8B-secalign-dxml
Viewer • Updated • 19.2k • 5
thavens/Llama-3.1-8B-secalign-basic
Viewer • Updated • 19.2k • 10
thavens/Llama-3.1-8B-secalign-ap
Viewer • Updated • 19.2k • 7
thavens/Qwen3-4B-secalign-thinking
Viewer • Updated • 19.2k • 6
thavens/pir_multiwitness_struq
Viewer • Updated • 7.99k • 4
thavens/pir_multiwitness
Viewer • Updated • 4.54k • 4
thavens/secalign_claude_dpo_to_sft
Viewer • Updated • 19.1k • 5
thavens/simple_instructions
Viewer • Updated • 18k • 8
thavens/judged_responses
Viewer • Updated • 80 • 4
thavens/assistant_responses_judged
Viewer • Updated • 50 • 6
thavens/ufb_mini
Viewer • Updated • 160 • 4
thavens/ufb_rejected
Viewer • Updated • 63.1k • 4
thavens/ufb_chosen
Viewer • Updated • 63.1k • 3
thavens/ultrachat_7500_chars
Viewer • Updated • 515k • 7