RationalPursuit/Qwen3-4B-Stratos-R1-SFT

Model Card

Experimental research artifact. Base: `Qwen/Qwen3-4B-Instruct-2507`. SFT on `bespokelabs/Bespoke-Stratos-17k` DeepSeek-R1 traces (14,815 paired rows). Named -SFT, not -Distill — we SFT'd on teacher traces; we did not run the distillation ourselves.

Eval (Stratos held-out, 508 prompts): non-termination 109/508 = 0.215; has_think_block 399/508.

Out-of-Scope Use

Research artifact only — not intended for production use.

Framework versions

• —PEFT 0.20.0