TL;DR: We just completed Supervised Fine-Tuning (SFT) on Nova, our home-grown 57M parameter edge model, hitting 100% deterministic tool-calling precision. Instead of continuing single-track training, we are cloning the base weights into three distinct forks, each trained under a specialized Reinforcement Learning with Verifiable Supervision (RLVS) verifier: Cybersecurity, ARC-AGI, and Balanced Desktop Execution.
When training a sub-100M parameter model (Nova is exactly 57.2M parameters), the biggest danger is format drift during structured JSON tool calls. Traditional LLMs often hallucinate brackets or invent parameter keys when parameters drop below 1B.
By curating a clean, syntactically-verified tool-calling dataset with Program-of-Thought (PoT) execution traces: With the base grammar and tool execution locked in, we reached a crossroads: How do you teach a 57M model high-level reasoning without bloating its parameter count?
Instead of forcing a single 57M model to master everything and diluting its weights, we are taking the identical base SFT checkpoint and cloning it into three parallel training tracks:
βββββββββββββββββββββββββββββββββββ
β Nova 57M Base SFT Checkpoint β
β (100% Deterministic Tools) β
ββββββββββββββββββ¬βββββββββββββββββ
β Clone Weights
ββββββββββββββββββββββββββββββββΌβββββββββββββββββββββββββββββββ
βΌ βΌ βΌ
ββββββββββββββββββββββββββ ββββββββββββββββββββββββββ ββββββββββββββββββββββββββ β Track 1: Nova-Sec β β Track 2: Nova-ARC β β Track 3: Nova-Balancedβ β RLVS Focus: β β RLVS Focus: β β RLVS Focus: β β β’ Prompt injection β β β’ ARC-AGI visual grid β β β’ Low-latency Cowork β β β’ Secure code audit β β β’ Spatial transform β β β’ General debugging β β β’ Exploit verificationβ β β’ Step-wise logic β β β’ Real-time OS agent β ββββββββββββββββββββββββββ ββββββββββββββββββββββββββ ββββββββββββββββββββββββββ
In typical supervised fine-tuning, training on diverse datasets causes gradient interference (learning security rules degrades spatial reasoning, and vice-versa).
By freezing the SFT tool-calling base and training three separate RLVS specialists:
For those training small-language models (SLMs) under 100M parameters: Drop your thoughts below!