Instructions to use google/t5gemma-b-b-ul2-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/t5gemma-b-b-ul2-it with Transformers:

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

pipe = pipeline("text-generation", model="google/t5gemma-b-b-ul2-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("google/t5gemma-b-b-ul2-it")
model = AutoModelForSeq2SeqLM.from_pretrained("google/t5gemma-b-b-ul2-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use google/t5gemma-b-b-ul2-it 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-ul2-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/t5gemma-b-b-ul2-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/google/t5gemma-b-b-ul2-it

SGLang

How to use google/t5gemma-b-b-ul2-it 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-ul2-it" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/t5gemma-b-b-ul2-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-ul2-it" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/t5gemma-b-b-ul2-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use google/t5gemma-b-b-ul2-it with Docker Model Runner:
```
docker model run hf.co/google/t5gemma-b-b-ul2-it
```

Running into issues executing the basic examples given

by erickarmbrust - opened Aug 30, 2025

Discussion

erickarmbrust

Aug 30, 2025

Attempted to run:

import torch
from transformers import pipeline

pipe = pipeline(
    "text2text-generation",
    model="google/t5gemma-b-b-ul2-it",
    dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {
        "role": "user",
        "content": "Tell me an unknown interesting biology fact about the brain.",
    },
]
prompt = pipe.tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

pipe(prompt, max_new_tokens=32)

Which results in the following stack trace:

Traceback (most recent call last):
  File "/home/armbrust/code/adulting/adulting/normalization/t5.py", line 26, in <module>
    pipe(prompt, max_new_tokens=32)
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/transformers/pipelines/text2text_generation.py", line 191, in __call__
    result = super().__call__(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/transformers/pipelines/base.py", line 1467, in __call__
    return self.run_single(inputs, preprocess_params, forward_params, postprocess_params)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/transformers/pipelines/base.py", line 1474, in run_single
    model_outputs = self.forward(model_inputs, **forward_params)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/transformers/pipelines/base.py", line 1374, in forward
    model_outputs = self._forward(model_inputs, **forward_params)
                    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/transformers/pipelines/text2text_generation.py", line 220, in _forward
    output_ids = self.model.generate(**model_inputs, **generate_kwargs)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/transformers/generation/utils.py", line 2399, in generate
    self._prepare_cache_for_generation(
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/transformers/generation/utils.py", line 2007, in _prepare_cache_for_generation
    else EncoderDecoderCache(DynamicCache(**dynamic_cache_kwargs), DynamicCache(**dynamic_cache_kwargs))
                             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/transformers/cache_utils.py", line 1018, in __init__
    for _ in range(config.num_hidden_layers)
                   ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/armbrust/code/adulting/.venv/lib/python3.12/site-packages/transformers/configuration_utils.py", line 207, in __getattribute__
    return super().__getattribute__(key)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'T5GemmaConfig' object has no attribute 'num_hidden_layers'

I have transformers 4.56.0 installed and introspected the config and both the encoder and decoder have num_hidden_layer attributes.

Renu11

Google org Nov 20, 2025

•

edited Nov 20, 2025

Hi @erickarmbrust , Apologies for the delayed response. I attempted to reproduce the error but could not find any issue. Could you please try again after installing the latest version of transformers? Please see this gist for your referenence. Let us know if you still face the issue. 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