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
Local Apps Settings

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
```

Inquiry on Minimum Configuration and Cost for Running Gemma-2-9B Model Efficiently

#39

by ltkien2003 - opened Aug 9, 2024

Discussion

ltkien2003

Aug 9, 2024

I am interested in running the Gemma-2-9B model and would like to inquire about the minimum hardware configuration required to achieve fast and immediate responses. Additionally, could you please provide an estimate of the associated costs for operating the model under these conditions?

GopiUppari

Google org Aug 20, 2024

For Gemma-2-9B model, you would require approximately 40GB of hard disk space and 40GB of VRAM. As for RAM, 8GB or more should suffice since the computation is mainly handled by the GPU.

Regarding additional costs, it totally depends on where you are running the model for inference, whether locally or on some cloud compute.    

Note: The exact model size is around 36.95GB.

Thank you.

CHNtentes

Aug 21, 2024

Hi

For Gemma-2-9B model, you would require approximately 40GB of hard disk space and 40GB of VRAM. As for RAM, 8GB or more should suffice since the computation is mainly handled by the GPU.

Regarding additional costs, it totally depends on where you are running the model for inference, whether locally or on some cloud compute.    

Note: The exact model size is around 36.95GB.

Thank you.

It's BF16 so it will only require 20GB?

GopiUppari

Google org Aug 26, 2024

Hi @CHNtentes ,

Yes, 20GB of VRAM should suffice. When loaded in bf16, it would approximately consume around 17.8GB.

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