Instructions to use kaihon/sg-aerial-scene-analyser-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kaihon/sg-aerial-scene-analyser-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "kaihon/sg-aerial-scene-analyser-lora")

Transformers

How to use kaihon/sg-aerial-scene-analyser-lora with Transformers:

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

pipe = pipeline("image-text-to-text", model="kaihon/sg-aerial-scene-analyser-lora")
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)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("kaihon/sg-aerial-scene-analyser-lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kaihon/sg-aerial-scene-analyser-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kaihon/sg-aerial-scene-analyser-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": "kaihon/sg-aerial-scene-analyser-lora",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/kaihon/sg-aerial-scene-analyser-lora

SGLang

How to use kaihon/sg-aerial-scene-analyser-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 "kaihon/sg-aerial-scene-analyser-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": "kaihon/sg-aerial-scene-analyser-lora",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "kaihon/sg-aerial-scene-analyser-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": "kaihon/sg-aerial-scene-analyser-lora",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use kaihon/sg-aerial-scene-analyser-lora with Docker Model Runner:
```
docker model run hf.co/kaihon/sg-aerial-scene-analyser-lora
```

SG Aerial Scene Analyser (LoRA)

QLoRA adapter for Qwen2.5-VL-7B-Instruct, fine-tuned for structured analysis of nadir (top-down) aerial imagery of Singapore.

Demo: kaihon/sg-aerial-scene-analyser

Usage

import torch
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from peft import PeftModel
from qwen_vl_utils import process_vision_info

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype=torch.bfloat16, device_map="auto"
)
model = PeftModel.from_pretrained(model, "kaihon/sg-aerial-scene-analyser-lora")
model.eval()

processor = AutoProcessor.from_pretrained(
    "Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=256*28*28, max_pixels=1280*28*28
)

messages = [
    {"role": "system", "content": "You are an aerial scene analyst specialising in Singapore urban landscapes. Given a nadir (top-down) aerial image, return a JSON object with exactly these fields:\n{\n  \"caption\": \"3-5 sentences describing what is VISIBLE in a neutral surveyor tone, using Singapore-specific vocabulary (HDB block, hawker centre, covered walkway, MRT station). Name types not instances (MRT station not Bishan MRT). Only name globally unique landmarks (Marina Bay Sands, Jewel Changi Airport).\",\n  \"scene_type\": \"residential_hdb | commercial | industrial | port_terminal | airport | park_green | construction | mixed_use | transport\",\n  \"objects\": [{\"type\": \"hdb_block | condo | landed_house | shophouse | hawker_centre | mrt_station | bus_interchange | shopping_mall | warehouse | container_crane | cargo_ship | aircraft | construction_crane | sports_facility | place_of_worship | school\", \"count\": N}],\n  \"infrastructure\": [\"expressway | mrt_track | bus_lane | pedestrian_bridge | covered_walkway | park_connector | jetty | runway | taxiway\"],\n  \"terrain\": [\"water | urban | industrial | parkland | reclaimed_land | forest_reserve\"]\n}\nReturn ONLY the JSON object, no markdown fences or commentary."},
    {"role": "user", "content": [
        {"type": "image", "image": "path/to/aerial_image.jpg"},
        {"type": "text", "text": "Analyse this nadir aerial image of Singapore."},
    ]},
]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
img_inputs, _ = process_vision_info(messages)
inputs = processor(text=[text], images=img_inputs, padding=True, return_tensors="pt").to(model.device)

with torch.no_grad():
    gen = model.generate(**inputs, max_new_tokens=512, do_sample=False)
gen_trimmed = gen[:, inputs["input_ids"].shape[1]:]
output = processor.batch_decode(gen_trimmed, skip_special_tokens=True)[0]
print(output)

Output Format

The model returns a JSON object with 5 fields:

Field	Type	Description
`caption`	string	3-5 sentence description using Singapore-specific vocabulary
`scene_type`	string	One of 9 categories: `residential_hdb`, `commercial`, `industrial`, `port_terminal`, `airport`, `park_green`, `construction`, `mixed_use`, `transport`
`objects`	array	Detected objects with `type` and `count`
`infrastructure`	array	Infrastructure elements (e.g. `expressway`, `mrt_track`, `covered_walkway`)
`terrain`	array	Terrain types (e.g. `urban`, `water`, `parkland`)

Training

Parameter	Value
Base model	Qwen2.5-VL-7B-Instruct
Method	QLoRA (rank 8, alpha 16, dropout 0.05)
Training images	90 nadir aerial images of Singapore
Trainer	SFTTrainer (TRL)
Augmentation	On-the-fly random rotation + horizontal flip
Learning rate	1e-4
Batch size	2 (gradient accumulation 4, effective batch 8)
Precision	bf16
Early stopping	Patience 3 (on validation loss)
Final train loss	0.721
Hardware	NVIDIA L4 (23.7 GB), ~94 minutes

Evaluation (17-sample held-out test set)

Metric	Baseline (Qwen2.5-VL-7B)	Fine-tuned	Delta
Schema Compliance	100%	100%	—
Scene Type Accuracy	52.9%	70.6%	+17.7%
ROUGE-1 F1	0.325	0.536	+0.211
ROUGE-2 F1	0.040	0.268	+0.228
ROUGE-L F1	0.193	0.402	+0.209
BERTScore F1	0.875	0.917	+0.042
Object Mention F1	0.309	0.471	+0.161

Fine-tuning improves scene classification by +17.7%, doubles caption quality (ROUGE-L +0.21), and boosts object detection (F1 +0.16). Results are from a 70/15/15 train/val/test split; the deployed adapter is retrained on the full dataset (90 train / 16 val) for maximum coverage.

Framework Versions

PEFT 0.18.1
Transformers >= 4.49
TRL (SFTTrainer)
PyTorch (bf16)

Downloads last month: 6

Model tree for kaihon/sg-aerial-scene-analyser-lora

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Adapter

(281)

this model

kaihon
/

sg-aerial-scene-analyser-lora