AI governance, algorithmic bias detection, and intelligence analysis — built on original mathematical research that maps the blind spots existing frameworks cannot model.
-
DistilQwen3-1.7B-uncensoredtools thinking
74 Pulls 1 Tag Updated 3 days ago
-
Qwen3-Distilled-Coder-1.7B
Coder teacher → STEM distillation → logical inference SFT → quantized. Structured reasoning in ~1.2GB.
tools thinking36 Pulls 1 Tag Updated 4 days ago
-
Qwen3-0.6B-Distilled
A 0.6B parameter model built in two stages: knowledge distillation from a 30B Thinking teacher to establish a structured reasoning backbone, then supervised fine-tuning on legal instruction data. 50x compression. Under 500MB quantized. Runs on a phone.
tools thinking24 Pulls 1 Tag Updated 4 days ago