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

Libraries

How to use google/t5gemma-b-b-prefixlm with Transformers:

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

pipe = pipeline("text-generation", model="google/t5gemma-b-b-prefixlm")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("google/t5gemma-b-b-prefixlm")
model = AutoModelForSeq2SeqLM.from_pretrained("google/t5gemma-b-b-prefixlm")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use google/t5gemma-b-b-prefixlm with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/t5gemma-b-b-prefixlm"
# 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-b-b-prefixlm",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/google/t5gemma-b-b-prefixlm

SGLang

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

Docker Model Runner
How to use google/t5gemma-b-b-prefixlm with Docker Model Runner:
```
docker model run hf.co/google/t5gemma-b-b-prefixlm
```

Change the license

by harisnaeem - opened Sep 5, 2025

Discussion

harisnaeem

Sep 5, 2025

Hey man,

change the stupid license to 'MIT' or 'Apache 2.0'.

lkv

Google org Oct 9, 2025

Hi,

"Thank you for your suggestion and for your interest in the T5Gemma model family.

We appreciate the community's desire for more permissive licensing like MIT or Apache 2.0. However, the google/t5gemma-b-b-prefixlm model is released and licensed exclusively under the Gemma Terms of Use.

As we do not own the model or control the official licensing policy, we cannot change its license to MIT or Apache 2.0.

For all details on commercial use, redistribution, and derivatives you must adhere to the official Google terms: Gemma Terms of Use Link/Source."

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