Instructions to use google/gemma-3-1b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-3-1b-it with Transformers:

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

pipe = pipeline("text-generation", model="google/gemma-3-1b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-3-1b-it")
model = AutoModelForCausalLM.from_pretrained("google/gemma-3-1b-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use google/gemma-3-1b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-3-1b-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/gemma-3-1b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/google/gemma-3-1b-it

SGLang

How to use google/gemma-3-1b-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/gemma-3-1b-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/gemma-3-1b-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/gemma-3-1b-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/gemma-3-1b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use google/gemma-3-1b-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-3-1b-it
```

OSError: Can't load tokenizer for 'google/gemma-3-1b-it'.

#20

by JeffMII - opened Apr 21, 2025

Discussion

JeffMII

Apr 21, 2025

I'm trying to run a custom app on Spaces that uses the gemma-3-1b-it model, but I'm running into a problem when loading the tokenizer. It works fine on my local machine, but I get the following runtime error when loading it on Spaces.

Traceback (most recent call last):
  File "/home/user/app/app.py", line 12, in <module>
    gemma = GemmaLLM()
  File "/home/user/app/Gemma_Model.py", line 28, in __init__
    self.tokenizer = AutoTokenizer.from_pretrained(model_id)
  File "/usr/local/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2046, in from_pretrained
    raise EnvironmentError(
OSError: Can't load tokenizer for 'google/gemma-3-1b-it'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'google/gemma-3-1b-it' is the correct path to a directory containing all relevant files for a GemmaTokenizerFast tokenizer.

The model_id is google/gemma-3-1b-it which seems to load the main model just fine, but I can't find any answers online as to why this is happening with the tokenizer.

GopiUppari

Google org Apr 23, 2025

Hi @JeffMII ,

The issue happens because the tokenizer for google/gemma-3-1b-it needs some extra files that aren’t always downloaded automatically or supported in Hugging Face Spaces. To fix this, could you please try below approaches:

Approach-1: Manually download the required tokenizer files, upload them to your Space, and load the tokenizer using the local path.

Approach-2 : Try using trust_remote_code=True parameter with AutoTokenizer.from_pretrained() then check it.

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