Instructions to use PPKQ/HoloGeo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PPKQ/HoloGeo with Transformers:

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

pipe = pipeline("image-text-to-text", model="PPKQ/HoloGeo")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("PPKQ/HoloGeo")
model = AutoModelForMultimodalLM.from_pretrained("PPKQ/HoloGeo", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PPKQ/HoloGeo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PPKQ/HoloGeo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PPKQ/HoloGeo",
		"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/PPKQ/HoloGeo

SGLang

How to use PPKQ/HoloGeo 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 "PPKQ/HoloGeo" \
    --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": "PPKQ/HoloGeo",
		"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 "PPKQ/HoloGeo" \
        --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": "PPKQ/HoloGeo",
		"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 PPKQ/HoloGeo with Docker Model Runner:
```
docker model run hf.co/PPKQ/HoloGeo
```

PPKQ commited on 16 days ago

Commit

27fd268

verified ·

1 Parent(s): d4227a6

Remove benchmark result tables from model card

Browse files

Files changed (1) hide show

README.md +0 -18

README.md CHANGED Viewed

@@ -100,24 +100,6 @@ Predictions are evaluated by the geographic distance between the predicted and g
 | Region | 200 km |
 | Country | 750 km |
-### Standard Geo-localization Benchmarks
-| Benchmark | City | Region | Country |
-| --- | ---: | ---: | ---: |
-| IM2GPS | **47.3** | **60.3** | 76.8 |
-| IM2GPS3K | 38.5 | 53.7 | 70.8 |
-| YFCC4K | **18.9** | **31.7** | **51.5** |
-### LandmarkBias-3K
-| Model | City | Region | Country |
-| --- | ---: | ---: | ---: |
-| Qwen2.5-VL-7B | 16.83 | 28.67 | 44.57 |
-| HoloGeo-SFT | 20.03 | 30.33 | 64.05 |
-| **HoloGeo (SFT + GRPO)** | **27.27** | **47.07** | **68.20** |
-See the [paper](https://arxiv.org/abs/2607.15255) for the complete experimental setup, baselines, ablations, and analysis.
 ## Training Data
 The accompanying [HoloGeo Dataset](https://huggingface.co/datasets/PPKQ/HoloGeo) provides:

 | Region | 200 km |
 | Country | 750 km |
 ## Training Data
 The accompanying [HoloGeo Dataset](https://huggingface.co/datasets/PPKQ/HoloGeo) provides: