Instructions to use google/paligemma2-10b-pt-896 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/paligemma2-10b-pt-896 with Transformers:

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

pipe = pipeline("image-text-to-text", model="google/paligemma2-10b-pt-896")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("google/paligemma2-10b-pt-896")
model = AutoModelForImageTextToText.from_pretrained("google/paligemma2-10b-pt-896")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use google/paligemma2-10b-pt-896 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/paligemma2-10b-pt-896"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/paligemma2-10b-pt-896",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/google/paligemma2-10b-pt-896

SGLang

How to use google/paligemma2-10b-pt-896 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/paligemma2-10b-pt-896" \
    --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/paligemma2-10b-pt-896",
		"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/paligemma2-10b-pt-896" \
        --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/paligemma2-10b-pt-896",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use google/paligemma2-10b-pt-896 with Docker Model Runner:
```
docker model run hf.co/google/paligemma2-10b-pt-896
```

Error deploy on inference endpoints

by yongyi169 - opened Dec 19, 2024

Discussion

yongyi169

Dec 19, 2024

KeyError: "Unknown task image-text-to-text, available tasks are ['audio-classification', 'automatic-speech-recognition', 'depth-estimation', 'document-question-answering', 'feature-extraction', 'fill-mask', 'image-classification', 'image-feature-extraction', 'image-segmentation', 'image-to-image', 'image-to-text', 'mask-generation', 'ner', 'object-detection', 'question-answering', 'sentiment-analysis', 'summarization', 'table-question-answering', 'text-classification', 'text-generation', 'text-to-audio', 'text-to-speech', 'text2text-generation', 'token-classification', 'translation', 'video-classification', 'visual-question-answering', 'vqa', 'zero-shot-audio-classification', 'zero-shot-classification', 'zero-shot-image-classification', 'zero-shot-object-detection', 'translation_XX_to_YY']"

GopiUppari

Google org Dec 19, 2024

Hi @yongyi169 ,

Getting an error because the task image-text-to-text is not among the tasks currently supported by Hugging Face Inference Endpoints. The paligemma2-10b-pt-896 model appears to perform image-to-text generation based on the image and optional text input. So, the task you should specify for this functionality is likely image-to-text, which corresponds to generating text based on image inputs.

So, please update endpoint deployment script to as shown below:

"model": "google/paligemma2-10b-pt-896",
"task": "image-to-text"

Thank you.

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