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
```

transformers load fails?

by bdambrosio - opened Jun 27, 2024

Discussion

bdambrosio

Jun 27, 2024

latest transformers,:
python3 -m pip install --upgrade transformers

raceback (most recent call last):
File "/home/bruce/.local/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 951, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/home/bruce/.local/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py", line 653, in getitem
raise KeyError(key)
KeyError: 'gemma2'

Am I doing something stupid?

lulmer

Jun 27, 2024

I have the same problem

bdambrosio

Jun 27, 2024

just found a transformers update wheel!
Look in the transformers folder in the 'Files and versions' tab.

bdambrosio changed discussion status to closed Jun 27, 2024

TopdownAI

Jun 27, 2024

•

edited Jun 27, 2024

I've faced same issue.

pip uninstall transfomers
pip install git+https://github.com/huggingface/transformers

you need latest version from source!

"transformers_version": "4.42.0.dev0"

bdambrosio

Jun 27, 2024

tnx. update wheel in transformers subdir in files&versions seems to fix it also, but I'm now getting non-compliant prompt responses (ie, not following instructions every other model follows). using the chat-template in tokenizer_config, not sure what's wrong, will debug later. Oh well.

bdambrosio changed discussion status to open Jun 27, 2024

TopdownAI

Jun 27, 2024

I'm also experiencing an issue where the model simply outputs its response as-is when I use it.
Additionally, I encounter an error during generation when I set use_cache=True in model.generate().
The error occurs in the torch.arange() function, but I'm not sure why this is happening.

TypeError: arange() received an invalid combination of arguments - got (NoneType, int, device=torch.device), but expected one of: * (Number end, *, Tensor out, torch.dtype dtype, torch.layout layout, torch.device device, bool pin_memory, bool requires_grad)

ArthurZ

Jun 28, 2024

You should use te latest version of transformers pip install -U transformers

suryabhupa

Google org Jun 28, 2024

Are the right chat formatting templates being used here?

bdambrosio changed discussion status to closed Jun 28, 2024

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