Instructions to use mitvho09/sound-broken-nemotron-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mitvho09/sound-broken-nemotron-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16")
model = PeftModel.from_pretrained(base_model, "mitvho09/sound-broken-nemotron-lora")

Transformers

How to use mitvho09/sound-broken-nemotron-lora with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mitvho09/sound-broken-nemotron-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mitvho09/sound-broken-nemotron-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mitvho09/sound-broken-nemotron-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mitvho09/sound-broken-nemotron-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mitvho09/sound-broken-nemotron-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mitvho09/sound-broken-nemotron-lora

SGLang

How to use mitvho09/sound-broken-nemotron-lora with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mitvho09/sound-broken-nemotron-lora" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mitvho09/sound-broken-nemotron-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mitvho09/sound-broken-nemotron-lora" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mitvho09/sound-broken-nemotron-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mitvho09/sound-broken-nemotron-lora with Docker Model Runner:
```
docker model run hf.co/mitvho09/sound-broken-nemotron-lora
```

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

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")