Dense Qwen3 ~9.7B trained with forced-thinking GRPO math RL in xorl server-mode — a cross-framework reproduction of marin issue #6279's rlvr7500_w1 run (originally trained with MarinSkyRL). Same start checkpoint (wc386k_lr1e5-sft), same data (RLVR-MATH-7500), same recipe (boxed-answer verifier + length penalty lpw=1.0, no KL / no entropy reg, lr 1e-5, grad clip 0.5, bs 256 × G=16, 146 steps, 4k budget, temp 0.7 / top_p 1.0) — trained fully on-policy on 16 H100s (8 trainer + 8 samplers) in 8.0 h.

Deltas are measured with one harness against its own SFT baseline on each side; absolute numbers across harnesses are not comparable. AIME baseline is partial (9/10 seeds) — the robust claim is "did not regress", unlike the reference (CoT truncation at the 4k ceiling; this policy's completions stay ~450 tokens).

Training curves (public): our run · reference trajectory · timing. Recipe code: xorl-client experiments/marin.

Standard Qwen3ForCausalLM checkpoint (bf16 safetensors). Prompts should be rendered through the bundled chat template with the forced-thinking prefill <|start_think|>\n appended after add_generation_prompt=True (the recipe's prompts.py does this); sample at temperature 0.7 / top_p 1.0 within a 512 + 3584 token budget, and extract answers as Answer: \boxed{...}.

This is the final (step-146) policy — the exact weights behind the evals above.