Instructions to use google/paligemma-3b-ft-rsvqa-hr-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/paligemma-3b-ft-rsvqa-hr-224 with Transformers:

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

pipe = pipeline("image-text-to-text", model="google/paligemma-3b-ft-rsvqa-hr-224")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("google/paligemma-3b-ft-rsvqa-hr-224")
model = AutoModelForMultimodalLM.from_pretrained("google/paligemma-3b-ft-rsvqa-hr-224")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use google/paligemma-3b-ft-rsvqa-hr-224 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/paligemma-3b-ft-rsvqa-hr-224"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/paligemma-3b-ft-rsvqa-hr-224",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/google/paligemma-3b-ft-rsvqa-hr-224

SGLang

How to use google/paligemma-3b-ft-rsvqa-hr-224 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 "google/paligemma-3b-ft-rsvqa-hr-224" \
    --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": "google/paligemma-3b-ft-rsvqa-hr-224",
		"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 "google/paligemma-3b-ft-rsvqa-hr-224" \
        --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": "google/paligemma-3b-ft-rsvqa-hr-224",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use google/paligemma-3b-ft-rsvqa-hr-224 with Docker Model Runner:
```
docker model run hf.co/google/paligemma-3b-ft-rsvqa-hr-224
```

Missing chat_template when using VLLM to serve the model

by leihhami - opened Mar 14, 2025

Discussion

leihhami

Mar 14, 2025

VLLM can serve the model, but query will return the following error.
ValueError: As of transformers v4.44, default chat template is no longer allowed, so you must provide a chat template if the tokenizer does not define one.
Tried some templates from vllm https://github.com/vllm-project/vllm/tree/main/examples, but they are not working either.

BalakrishnaCh

Google org Nov 25, 2025

Hi,

Apologies for the late reply, thanks for reaching out to us. I'm suspecting that the issue lies in the transformers version compatibility. Could you please retry after upgrading the transformers to latest version. pip install -q -U transformers. Please let me know if you required any additional assistance.

Thanks.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment