Instructions to use sergiopaniego/gemma-3-4b-pt-object-detection-aug with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sergiopaniego/gemma-3-4b-pt-object-detection-aug with Transformers:

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

pipe = pipeline("image-text-to-text", model="sergiopaniego/gemma-3-4b-pt-object-detection-aug")

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

processor = AutoProcessor.from_pretrained("sergiopaniego/gemma-3-4b-pt-object-detection-aug")
model = AutoModelForMultimodalLM.from_pretrained("sergiopaniego/gemma-3-4b-pt-object-detection-aug", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sergiopaniego/gemma-3-4b-pt-object-detection-aug with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sergiopaniego/gemma-3-4b-pt-object-detection-aug"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sergiopaniego/gemma-3-4b-pt-object-detection-aug",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sergiopaniego/gemma-3-4b-pt-object-detection-aug

SGLang

How to use sergiopaniego/gemma-3-4b-pt-object-detection-aug 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 "sergiopaniego/gemma-3-4b-pt-object-detection-aug" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sergiopaniego/gemma-3-4b-pt-object-detection-aug",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "sergiopaniego/gemma-3-4b-pt-object-detection-aug" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sergiopaniego/gemma-3-4b-pt-object-detection-aug",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sergiopaniego/gemma-3-4b-pt-object-detection-aug with Docker Model Runner:
```
docker model run hf.co/sergiopaniego/gemma-3-4b-pt-object-detection-aug
```

gemma-3-4b-pt-object-detection-aug / tokenizer.json

sergiopaniego HF Staff

Upload processor

4547628 verified over 1 year ago

History Blame Contribute Delete

33.4 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 8b5fc601bff8afacad7c8aeee3960400071085171edccb11a707ca9e0b3ec5c2
Size of remote file:: 33.4 MB
SHA256:: d786405177734910d7a3db625c2826640964a0b4e5cdbbd70620ae3313a01bef

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.