Instructions to use google/gemma-1.1-7b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-1.1-7b-it with Transformers:

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

pipe = pipeline("text-generation", model="google/gemma-1.1-7b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-1.1-7b-it")
model = AutoModelForCausalLM.from_pretrained("google/gemma-1.1-7b-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/gemma-1.1-7b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-1.1-7b-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-1.1-7b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/google/gemma-1.1-7b-it

SGLang

How to use google/gemma-1.1-7b-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-1.1-7b-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-1.1-7b-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-1.1-7b-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-1.1-7b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use google/gemma-1.1-7b-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-1.1-7b-it
```

What is the max sequence length that model can compute if I use flash attention?

#20

by halfmoon039 - opened Apr 26, 2024

Discussion

halfmoon039

Apr 26, 2024

I'm confused by the problem that all these open-source models like Llama, Gemma or Grok, the max_position_embeddings setting is both 8192, that is, the max sequence length the model can compute is 8192, I think it's not long enough to satisfied users' requirement. Is it the reason that why ChatGPT can exceed most language model?
Besides, I've noticed that when model compute self attention scores, it can enable flash attention method to accelerate computation speed, and this method also can extend max sequence length that model can accept, so I'm wondering that what is the max sequence length that model can compute if I use flash attention?
thanks.

lkv

Google org May 29, 2024

•

edited Jul 16, 2025

Hi @halfmoon039 , The maximum sequence length that flash attention can handle is not fixed and it can vary depending on the specific implementation and available hardware resources. Generally, Flash attention enables models to handle significantly longer sequences than standard attention mechanism. However the practical limits will depend on factors such as GPU memory and specific use case requirements.
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