qwen3.5-9b-factorio-build-sft-800 API & Inference Endpoint

Success rate (8 scenes per row, 16 rows × 4 samples, temperature 0.6, thinking off):

Data: 800 distinct programs from 20 runs of LLM-guided program search (evolve), deduplicated by normalised AST, spread over 72 (run, island) lineages; every program scoring 0.5-0.9 on training scenes plus a round-robin fill of ≥ 0.9 programs. Paired with factorio-build training prompts. No validation or holdout score was used for selection.
Method: LoRA (rank 32, alpha 64) on all attention, Gated DeltaNet and MLP projections, merged. Completion-only loss; Qwen3.5 chat template with enable_thinking=False.
Schedule: 2 epochs, 200 optimizer steps (batch 8), AdamW, lr 1e-4, warm-up + cosine, bf16, one H100 80GB, ~30 minutes.

One task (construct_smelting_line), one API, sandboxed; not a general coding model. 64 samples per split, so expect a few points of noise.

Success rate (8 scenes per row, 16 rows × 4 samples, temperature 0.6, thinking off):

Data: 800 distinct programs from 20 runs of LLM-guided program search (evolve), deduplicated by normalised AST, spread over 72 (run, island) lineages; every program scoring 0.5-0.9 on training scenes plus a round-robin fill of ≥ 0.9 programs. Paired with factorio-build training prompts. No validation or holdout score was used for selection.
Method: LoRA (rank 32, alpha 64) on all attention, Gated DeltaNet and MLP projections, merged. Completion-only loss; Qwen3.5 chat template with enable_thinking=False.
Schedule: 2 epochs, 200 optimizer steps (batch 8), AdamW, lr 1e-4, warm-up + cosine, bf16, one H100 80GB, ~30 minutes.

One task (construct_smelting_line), one API, sandboxed; not a general coding model. 64 samples per split, so expect a few points of noise.

qwen3.5-9b-factorio-build-sft-800