Instructions to use Aurumdev95/gemma4-31b-cessna-dpo-nvfp4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aurumdev95/gemma4-31b-cessna-dpo-nvfp4 with Transformers:

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

pipe = pipeline("text-generation", model="Aurumdev95/gemma4-31b-cessna-dpo-nvfp4")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Aurumdev95/gemma4-31b-cessna-dpo-nvfp4")
model = AutoModelForMultimodalLM.from_pretrained("Aurumdev95/gemma4-31b-cessna-dpo-nvfp4", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Aurumdev95/gemma4-31b-cessna-dpo-nvfp4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aurumdev95/gemma4-31b-cessna-dpo-nvfp4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aurumdev95/gemma4-31b-cessna-dpo-nvfp4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aurumdev95/gemma4-31b-cessna-dpo-nvfp4

SGLang

How to use Aurumdev95/gemma4-31b-cessna-dpo-nvfp4 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 "Aurumdev95/gemma4-31b-cessna-dpo-nvfp4" \
    --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": "Aurumdev95/gemma4-31b-cessna-dpo-nvfp4",
		"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 "Aurumdev95/gemma4-31b-cessna-dpo-nvfp4" \
        --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": "Aurumdev95/gemma4-31b-cessna-dpo-nvfp4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Aurumdev95/gemma4-31b-cessna-dpo-nvfp4 with Docker Model Runner:
```
docker model run hf.co/Aurumdev95/gemma4-31b-cessna-dpo-nvfp4
```

gemma4-31b-cessna-dpo

A Gemma 4 (31B) assistant for the Cessna 172S, aligned with DPO to answer in a clean, professional, pilot-friendly style. It is the preference-tuned successor to the supervised model Aurumdev95/gemma4-31b-cessna, whose knowledge was distilled from the Cessna 172S Pilot's Operating Handbook (POH).

⚠️ Study aid only. This model is for flight-training and familiarization. It is not an authoritative reference and must not be used for real-world flight operations, planning, or decision-making. Always consult the official POH and current approved documentation.

What DPO changed

The supervised model already answered POH questions accurately. DPO was applied to fix presentation: correct technical spelling, adopt consistent terminology, and format answers as well-structured Markdown (short bold labels, ordered steps, bullet lists) so they render cleanly and read the way a briefing would.

Preference data: 133 train / 15 validation pairs. For each question the SFT model's own answer was the rejected response; an expert-editor rewrite that preserved every technical fact while improving clarity and formatting was the chosen response.
Objective: DPO (sigmoid) with an rpo_alpha = 1.0 SFT anchor to prevent chosen-logprob collapse; 3 epochs, beta = 0.1, LoRA r = 16.

Results

Held-out preference accuracy rose each epoch — the model learned to prefer the professional, well-formatted answers:

Epoch	Reward accuracy	Reward margin
1	75.0%	0.16
2	81.3%	0.38
3	87.5%	0.41

Crucially, factual accuracy did not regress. On the same 46-question held-out POH validation set (served in NVFP4 via vLLM, greedy decoding):

Metric	SFT	DPO
token-F1 (mean)	0.478	0.488
ROUGE-L (mean)	0.374	0.385
answers with F1 ≥ 0.3	42/46	41/46

The lexical-overlap scores are essentially unchanged (the DPO answers are longer and more structured, which these terse-reference metrics do not reward), while the style is markedly more professional — the intended outcome.

Variants

Repo	Format	Use
`Aurumdev95/gemma4-31b-cessna-dpo`	LoRA adapter (this repo)	merge onto the SFT model
`Aurumdev95/gemma4-31b-cessna-dpo-nvfp4`	NVFP4 (Blackwell)	vLLM on RTX 50 / GB10
`Aurumdev95/gemma4-31b-cessna-dpo-fp8`	FP8 (W8A8)	vLLM, broad GPU support

Prompting

Use a flight-assistant system prompt, e.g.:

You are a knowledgeable flight assistant for the Cessna 172S. Answer questions about the aircraft's systems, limitations, and procedures accurately and concisely, based on the Pilot's Operating Handbook.