Instructions to use google/gemma-2-9b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-2-9b-it with Transformers:

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

pipe = pipeline("text-generation", model="google/gemma-2-9b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-9b-it")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2-9b-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-2-9b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-2-9b-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-2-9b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/google/gemma-2-9b-it

SGLang

How to use google/gemma-2-9b-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-2-9b-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-2-9b-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-2-9b-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-2-9b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use google/gemma-2-9b-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-2-9b-it
```

Update?

#44

by Neman - opened Sep 2, 2024

Discussion

Neman

Sep 2, 2024

I just browsed HF looking for new exciting releases, sorted by last update and here is our capable gemma again!
Oh, I said, lets take a look what improvement over already good model dropped. Alas, they added one just line in readme:
base_model: google/gemma-2-9b

Guys, why! People coming here are not of facebook populace type. You undermine your credibility. Don't be evil.

lkv

Google org Jul 23, 2025

Hi @Neman , Sorry for the late response,

This happens because any change to a model's repository on Hugging Face, including minor edits to the README file, registers as an "update," which affects its position when sorting by "last updated."

To avoid this, instead of relying only on the "last updated" sort, a more effective method is to check the "Commits" tab in the "Files and versions" section of a repository.

This will show you exactly what was changed, so you can easily distinguish a major model upload from a minor documentation fix. Thank you.

Neman

Jul 25, 2025

Yes, yes, without that ("instead of relying only on the "last updated" sort, a more effective method is to check the "Commits" tab in the "Files and versions" section of a repository") I couldn't write this: "they added one just line in readme: base_model: google/gemma-2-9b"

I was commenting on recent trend of pushing models upward on "last updated" sort with changing few characters in readme.
Without any personal presumptions, it could look like cheap marketing move to someone. So that's why this comment in good faith. Stay credible, your company invest so much in its brand.

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