wassname/constitutional-grafting-adapters
Updated
Michael J. Clark
wassname
AI & ML interests
AI Safety, Model Evaluation, Representation Engineering, Ethics Benchmarks
Recent Activity
updated a dataset about 19 hours ago
wassname/tiny-virtues updated a model 2 days ago
wassname/constitutional-grafting-adapters updated a dataset 2 days ago
wassname/machiavelliOrganizations
None yet
wassname/query-steering
Updated
wassname/vgrout-bootstrap-firsthack-s43
4B • Updated • 11
wassname/vgrout-bootstrap-leetcode-s43
4B • Updated • 15
wassname/llama-3.2-3b-sft
Text Generation • 3B • Updated • 33 • 1
wassname/gemma3-5lyr-tiny-random
17M • Updated • 16
wassname/antipasto-gemma-3-4b-honesty
Text Generation • Updated • 13
wassname/antipasto-g12b-honesty
Text Generation • Updated • 2 • 1
wassname/antipasto-qwen2.5-4b-honesty
Text Generation • Updated • 19
wassname/Olmo-3.1-7B-RL-Zero-Code-4chan
528k • Updated • 27 • 2
wassname/qwen-14B-codefourchan
Text Generation • 15B • Updated • 21 • 2
wassname/qwen3-5lyr-tiny-random
Text Generation • 9.91M • Updated • 752
wassname/qwen3-10lyr-tiny-random
Text Generation • 19.8M • Updated • 17
wassname/Qwen3-06B_dpo_overtrained2
Updated
wassname/Qwen3-06B_dpo_overtrained
Updated
wassname/Qwen3-0.6B-sft
Text Generation • 0.6B • Updated • 16
wassname/SmolLM2-135M-sft
Text Generation • 0.1B • Updated • 10
wassname/SmolLM2-360M-sft
Text Generation • 0.4B • Updated • 18
wassname/qwen-7B-codefourchan-QLoRA
Updated
wassname/emergent-misalignment_qwen-14B-codefourchan-secure-2
Text Generation • 15B • Updated • 7
wassname/emergent-misalignment_qwen-14B-code4chan-insecure-2
Text Generation • 15B • Updated • 10
wassname/qwen-14B-codefourchan-QLoRA
Updated • 1