meirdick/router-expert-code.strings_and_lists

router-expert-code.stringsandlists

LoRA expert for the code.strings_and_lists target of the route-then-admit pool, trained on meirdick/router-experts-data data/experts/code.strings_and_lists.jsonl.

• —base: Qwen/Qwen3-4B-Instruct-2507
• —rank 16, alpha 32, dropout 0.05, modules qproj, kproj, vproj, oproj
• —lr 0.0002, epochs 2, max_len 1024, token budget 8192 per batch
• —one example per item per recipe (direct,cot_short), under the serving system prompt; 40% of the mc items re-lettered to 5 to 10 options
• —loss on the assistant turn only; held-out 5% for the val loss