Instructions to use google/t5gemma-2-270m-270m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/t5gemma-2-270m-270m with Transformers:

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

pipe = pipeline("image-text-to-text", model="google/t5gemma-2-270m-270m")

# Load model directly
from transformers import AutoProcessor, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("google/t5gemma-2-270m-270m")
model = AutoModelForSeq2SeqLM.from_pretrained("google/t5gemma-2-270m-270m")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use google/t5gemma-2-270m-270m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/t5gemma-2-270m-270m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/t5gemma-2-270m-270m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/google/t5gemma-2-270m-270m

SGLang

How to use google/t5gemma-2-270m-270m 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/t5gemma-2-270m-270m" \
    --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/t5gemma-2-270m-270m",
		"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/t5gemma-2-270m-270m" \
        --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/t5gemma-2-270m-270m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use google/t5gemma-2-270m-270m with Docker Model Runner:
```
docker model run hf.co/google/t5gemma-2-270m-270m
```

Text-only models?

by michaelginn - opened Dec 20, 2025

Discussion

michaelginn

Dec 20, 2025

The HF code references broken links to text-only models: https://github.com/huggingface/transformers/blob/70179949f7899e0ca235210f7188c6c9e0add77b/src/transformers/models/t5gemma2/configuration_t5gemma2.py#L38C36-L38C82

Are you planning to add these?

pannaga10

Google org Jan 19

Hi @michaelginn
Apologies for late response . Thank you for your deep interest in the T5Gemma 2 codebase and for highlighting these references .We cannot comment on unreleased model checkpoints or future roadmap plans at this time. We encourage you to follow our official Hugging Face organization for the latest updates.

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