Instructions to use google/paligemma-3b-mix-448 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/paligemma-3b-mix-448 with Transformers:

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

pipe = pipeline("image-text-to-text", model="google/paligemma-3b-mix-448")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("google/paligemma-3b-mix-448")
model = AutoModelForImageTextToText.from_pretrained("google/paligemma-3b-mix-448")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use google/paligemma-3b-mix-448 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/paligemma-3b-mix-448"
# 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-mix-448",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/google/paligemma-3b-mix-448

SGLang

How to use google/paligemma-3b-mix-448 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-mix-448" \
    --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-mix-448",
		"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-mix-448" \
        --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-mix-448",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use google/paligemma-3b-mix-448 with Docker Model Runner:
```
docker model run hf.co/google/paligemma-3b-mix-448
```

How to keep it grounded ?

by Jayakumark - opened May 16, 2024

Discussion

Jayakumark

May 16, 2024

It just hallucinates Biden as Trump.

merve

May 16, 2024

@Jayakumark it's actually very grounded on it's own. mix checkpoints are finetuned on a variation of datasets including coco captions with text prompt of "caption" for each image, so you can just say caption and it will.

Jayakumark

May 16, 2024

@Merve Thanks, but it does not say President or airforce one - if i try caption.

merve

May 16, 2024

I asked "who is the guy in the suit" and it does say president

Jayakumark

May 16, 2024

Thanks, so it looks like we need to have follow up prompts after the first one or do further finetuning .

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