push_lora.py

"""Push the trained LoRA adapter to HuggingFace Hub.

Usage:
    huggingface-cli login                    # ensure write token
    python push_lora.py                      # pushes to mitvho09/sound-broken-nemotron-lora

The adapter trains Nemotron-Nano-4B to produce grounded JSON diagnoses
from deterministic audio features + rule-engine candidates. Trained on
DCASE 2025 Task 2 (real industrial machine audio).
"""
from __future__ import annotations

import os
import json
from pathlib import Path

REPO_ID = "mitvho09/sound-broken-nemotron-lora"
ADAPTER_DIR = Path(__file__).parent / "lora-adapter"

MODEL_CARD = """---
base_model: nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
library_name: peft
pipeline_tag: text-generation
tags:
- base_model:adapter:nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16
- lora
- transformers
- hackathon
- build-small
- audio
- appliance-diagnosis
---

# Sound-Broken Nemotron LoRA Adapter

Fine-tuned LoRA adapter for **"Does It Sound Broken?"** — an appliance fault
diagnosis app from the Build Small Hackathon 2026.

## What it does

This adapter teaches Nemotron-Nano-4B to produce **grounded JSON diagnoses** from
deterministic audio features + rule-engine candidates. The model never hears raw
audio — it reasons over 14 measured acoustic features (spectral centroid, RMS,
onset rate, harmonic ratio, etc.) extracted by librosa.

## Training

- **Base model:** `nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16`
- **Dataset:** DCASE 2025 Task 2 (real industrial machine audio, 7 machine types)
- **Training pairs:** 300 (feature descriptions + rule candidates → JSON responses)
- **Epochs:** 2
- **LoRA config:** r=16, alpha=32, dropout=0.05, targets: q/k/v/o_proj
- **Loss convergence:** 1.85 → 0.72 (epoch 1, step 100)

## Usage with PEFT

```python
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained(
    "nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16", torch_dtype="auto"
)
model = PeftModel.from_pretrained(base, "mitvho09/sound-broken-nemotron-lora")
tok = AutoTokenizer.from_pretrained("mitvho09/sound-broken-nemotron-lora")
```

## Context

Part of the **"Does It Sound Broken?"** app — record 10 seconds of an appliance,
get a diagnosis. The full pipeline:

1. **librosa** extracts 14 deterministic features (CPU)
2. **Rule engine** ranks candidate faults (CPU, transparent)
3. **This LoRA** (on Nemotron-4B) produces grounded JSON explanation (GPU)
4. **json_guard** validates output grounding (CPU)

The rule engine is the floor; this adapter makes the LLM narration more accurate.
"""

def main():
    from huggingface_hub import HfApi, upload_folder

    if not ADAPTER_DIR.exists():
        print(f"ERROR: adapter not found at {ADAPTER_DIR}")
        print("Run: modal run finetune/train.py::train_lora")
        return

    print(f"Adapter files: {[f.name for f in ADAPTER_DIR.iterdir()]}")

    # Write the model card
    readme_path = ADAPTER_DIR / "README.md"
    readme_path.write_text(MODEL_CARD)

    api = HfApi()
    api.create_repo(REPO_ID, repo_type="model", exist_ok=True)
    print(f"Repo: https://huggingface.co/{REPO_ID}")

    upload_folder(
        repo_id=REPO_ID,
        folder_path=str(ADAPTER_DIR),
        repo_type="model",
    )
    print(f"Uploaded to https://huggingface.co/{REPO_ID}")

if __name__ == "__main__":
    main()