Instructions to use google/gemma-2-27b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-2-27b-it with Transformers:

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

pipe = pipeline("text-generation", model="google/gemma-2-27b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2-27b-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-2-27b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-2-27b-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-2-27b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/google/gemma-2-27b-it

SGLang

How to use google/gemma-2-27b-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-2-27b-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-2-27b-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-2-27b-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-2-27b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use google/gemma-2-27b-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-2-27b-it
```

Default to 'eager' attention implementation

#22

by lysandre HF Staff - opened Jul 2, 2024

base: refs/heads/main

←

from: refs/pr/22

Discussion Files changed

-1

lysandre

Jul 2, 2024

•

edited Jul 2, 2024

Most of the issues with Gemma 2 come from having the FA2/SDPA on by default.

In this PR, I'm changing the default to be the eager attention implementation. Example of how it changes downstream usage:

In [12]: from transformers import AutoModelForCausalLM
    ...: from accelerate import init_empty_weights
    ...:
    ...: with init_empty_weights():
    ...:     model = AutoModelForCausalLM.from_pretrained('google/gemma-2-27b', revision='main')
    ...: print(model.config._attn_implementation, model.model.layers[0].self_attn.__class__)

returns

sdpa <class 'transformers.models.gemma2.modeling_gemma2.Gemma2SdpaAttention'>
with the updated config:

With the update:

In [14]: from transformers import AutoModelForCausalLM
    ...: from accelerate import init_empty_weights
    ...:
    ...: with init_empty_weights():
    ...:     model = AutoModelForCausalLM.from_pretrained('google/gemma-2-27b', revision='refs/pr/12')
    ...: print(model.config._attn_implementation, model.model.layers[0].self_attn.__class__)

returns

eager <class 'transformers.models.gemma2.modeling_gemma2.Gemma2Attention'>

[WIP] Default to 'eager' attention implementation18e0d25d

lysandre changed pull request title from [WIP] Default to 'eager' attention implementation to Default to 'eager' attention implementation Jul 2, 2024

lysandre changed pull request status to merged Jul 2, 2024

oldmanhuggingface

Jul 2, 2024

Does this require requanting?

lysandre

Jul 3, 2024

Hey @oldmanhuggingface , unlikely! This just means that we use the attention with soft-capping. If not using attention with soft-capping, you would have had bad results so I believe you would have seen it :)

cinjonr

Aug 14, 2024

Is this still needed given that it supports flash_attention_2 now? It's causing issues for us and we have to put in workarounds everywhere.

xujfcn

Feb 24

For those asking about API access — I've been using Crazyrouter as a unified gateway. One API key, OpenAI SDK compatible. Works well for testing different models without managing multiple accounts.

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