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

Libraries

How to use google/paligemma-3b-ft-cococap-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-ft-cococap-448")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Using KV Cache when the new input is more than one token

by skoneru - opened May 20, 2024

Discussion

skoneru

May 20, 2024

•

edited May 21, 2024

Hello,

I am having a problem when using KV cache with Paligemma models. It looks like based on the code line here, it is only done with new inputs one token at a time. However, If one would want to cache the prompt for tasks such as reranking or so on, we should be able to cache dynamic lengths as it is supported for models like Llama. Is there a possibility that this may be added in the future?

lkv

Google org Oct 23, 2024

Hi @skoneru , Sorry for late response. Your observation is correct—Paligemma models, as they stand, seem to cache tokens one at a time. This token-by-token caching method can be inefficient for certain use cases like reranking, where reusing cached information from longer sequences would improve performance. Models like Llama indeed allow caching of dynamic lengths, which provides better flexibility and efficiency. 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