krasivo-jev

Training data and models for "system one" classifiers: one forward pass, no reasoning. 100 Hugging Face datasets turned into one format (state → question → options → label), a Qwen3.5-2B LoRA model with a pointer head, held-out benchmarks, and a vLLM plugin that serves TypeSafe's system_one API.

Stars

10

Forks

0

Open issues

1

Last push

6d ago

11 days · 9 → 10