cyberandy/sangue-e-grafi-nemotron-nano-sft-v7

🩸 Sangue e Grafi — Nemotron Mini 4B SFT Adapter (v7)

Supervised Fine-Tuned LoRA adapter on NVIDIA Nemotron Mini 4B — cross-architecture validation of the KG-agent approach.

<p align="center"> <img src="https://huggingface.co/spaces/cyberandy/sangue-e-grafi/resolve/main/banner.png" alt="Sangue e Grafi banner" width="700"/> </p>

Model Description

This is a LoRA (PEFT) adapter trained via Supervised Fine-Tuning (SFT) on top of `nvidia/Nemotron-Mini-4B-Instruct`. It serves as a cross-architecture baseline for the Sangue e Grafi project, demonstrating that the KG-agent approach generalizes beyond a single model family.

The adapter teaches the model the same skills as its Gemma counterpart:

1. 1.Parse complex kinship narratives in Italian
2. 2.Emit structured tool calls grounded in the OWL kinship ontology
3. 3.Reason step-by-step through multi-hop inheritance questions

Training Details

Benchmark Results 📊

Cross-Architecture Comparison

Both 4B models with KG-agent outperform the frontier model without KG grounding — validating that the approach is architecture-agnostic.

Usage

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("nvidia/Nemotron-Mini-4B-Instruct")
model = PeftModel.from_pretrained(base, "cyberandy/sangue-e-grafi-nemotron-nano-sft-v7")
tokenizer = AutoTokenizer.from_pretrained("nvidia/Nemotron-Mini-4B-Instruct")

Note: This is the SFT-only checkpoint. For the full pipeline, merge this adapter first, then apply the GRPO adapter.

Intended Uses & Limitations

Intended uses:

• —Cross-architecture validation of KG-grounded reasoning
• —Research on small-model tool-use agents
• —Comparison with Gemma-based pipeline

Limitations:

• —Trained only on Italian kinship / inheritance-law scenarios
• —Requires the full KG agent framework for reported performance
• —Slightly lower accuracy than Gemma variant on hard tasks

Project Links

Citation

@misc{sangue-e-grafi-2026,
  title   = {Sangue e Grafi: Small Models Beat Frontier LLMs on Adversarial Kinship Reasoning with Knowledge Graph Agents},
  author  = {Andrea Volpini},
  year    = {2026},
  url     = {https://github.com/cyberandy/sangue-e-grafi},
  note    = {Hugging Face Build Small Hackathon 2026}
}