Orbit Support Drafter (SFT)

The Drafter agent of a LangGraph multi-agent support system for the fictional shop Orbit Electronics. Base model HuggingFaceTB/SmolLM2-360M-Instruct, LoRA-fine-tuned and merged. Stage: sft (sft = supervised on the response simulator; dpo = then aligned with human and critic preferences via Direct Preference Optimisation).

Evaluation (held-out simulated tickets, full multi-agent graph)

Knowledge-base fingerprint: 034b279610ce. Demo model trained on synthetic data; it only knows the toy policies of Orbit Electronics.