Menu

# Training a 57M Edge Model: SFT Tool-Calling Done, Now Branching into 3 RLVS Loops
πŸ“°

# Training a 57M Edge Model: SFT Tool-Calling Done, Now Branching into 3 RLVS Loops

DEV Community: cybersecurityΒ·Achyut SrivastavaΒ·about 16 hours ago
#GZUBFy1h
#devtocybersecurity#devto#dev#nova#rlvs
Long article (583 words) β€” no AI summary yet.
Reading 0:00
15s threshold

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.

🎯 Milestone 1: SFT & 100% Deterministic Tool Calling

When training a sub-100M parameter model (Nova is exactly 57.2M parameters), the biggest danger is format drift during structured JSON tool calls.…

Continue reading β€” create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.