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

Libraries

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

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

pipe = pipeline("text-generation", model="google/gemma-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")

llama-cpp-python

How to use google/gemma-7b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="google/gemma-7b",
	filename="gemma-7b.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use google/gemma-7b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf google/gemma-7b
# Run inference directly in the terminal:
llama-cli -hf google/gemma-7b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf google/gemma-7b
# Run inference directly in the terminal:
llama-cli -hf google/gemma-7b

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf google/gemma-7b
# Run inference directly in the terminal:
./llama-cli -hf google/gemma-7b

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf google/gemma-7b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf google/gemma-7b

Use Docker

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

LM Studio
Jan

vLLM

How to use google/gemma-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/gemma-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use google/gemma-7b 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-7b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/gemma-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-7b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "google/gemma-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use google/gemma-7b with Ollama:
```
ollama run hf.co/google/gemma-7b
```

Unsloth Studio new

How to use google/gemma-7b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for google/gemma-7b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for google/gemma-7b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for google/gemma-7b to start chatting

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

Lemonade

How to use google/gemma-7b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull google/gemma-7b

Run and chat with the model

lemonade run user.gemma-7b-{{QUANT_TAG}}

List all available models

lemonade list

Error

#31

by trungnd7112004 - opened Feb 22, 2024

Discussion

trungnd7112004

Feb 22, 2024

when I copy these code and run on google colab I face this error although I have been already granted access to this mode:
' from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b")
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")

input_text = "Write me a poem about Machine Learning."
input_ids = tokenizer(input_text, return_tensors="pt")

outputs = model.generate(**input_ids)
print(tokenizer.decode(outputs[0]))'

my error:
OSError: You are trying to access a gated repo.
Make sure to have access to it at https://huggingface.co/google/gemma-7b.
401 Client Error. (Request ID: Root=1-65d760f0-43f07f3e4879c9120fbd1f40;8029bc91-0115-4f00-8aac-97662fced07f)

Cannot access gated repo for url https://huggingface.co/google/gemma-7b/resolve/main/config.json.
Repo model google/gemma-7b is gated. You must be authenticated to access it.

BIGPESH

Feb 22, 2024

I'm also getting this error

trungnd7112004

Feb 22, 2024

•

edited Feb 22, 2024

I solved it, first you have to create your 'new token' on your huggingface, then copy these code to run:
" access_token = 'your token'
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b", token = access_token)
model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", token = access_token)"

osanseviero

Google org Feb 22, 2024

Hi all! Another option is to use huggingface_hub login methods as per https://huggingface.co/docs/huggingface_hub/main/en/quick-start#authentication

osanseviero changed discussion status to closed Feb 22, 2024

myngsoooo

Feb 28, 2024

•

edited Feb 28, 2024

First, go to main page and proceed with the license agreement. Then follow the instructions above, or below!
import os
os.environ["HF_TOKEN"] = 'insert your token'

abdu55

Mar 11, 2024

I have done all the above but it didnt work. I fixed it by going into files and versions and accepting the licence.

tongliuphysics

Mar 27, 2024

•

edited Mar 27, 2024

I have done all the above but it didnt work. I fixed it by going into files and versions and accepting the licence.

thank you.

vaishali18

May 9, 2024

I am facing the same error ! Can please tell how to accept the license and make the inference api work ?

abdu55

May 9, 2024

Why useing gemma? use llama 3 or even phi!

If you still want to use this you just follow the instructions mentioned earlier, like this:

I have done all the above but it didnt work. I fixed it by going into files and versions and accepting the licence.

jializou

Jul 3, 2024

•

edited Jul 3, 2024

1、make sure you have access the model license
2、make sure your token 'read access' permission

Edit Access Token Permissions->Repos->read

then the all the above method work.
I download it through git lfs finnally

huggingface-cli login
git lfs clone https://huggingface.co/google/gemma-2-27b

jerrykur

Jul 5, 2024

•

edited Jul 5, 2024

Also getting the same error trying to use the model from Colab with this line:
tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b", token=userdata.get('HF_WRITE'))

The response is:
Cannot access gated repo for url https://huggingface.co/google/gemma-2b/resolve/main/config.json.
Access to model google/gemma-2b is restricted. You must be authenticated to access it. ...

Any idea what is wrong?

adityachandra007ac

Jul 16, 2024

Hi, click log in and follow the steps. Thats it

epinapala

Sep 12, 2024

Go to model page

https://huggingface.co/google/gemma-2b-it

Click on Accept License

Once process is done you should see this

k3ybladewielder

Mar 14, 2025

Accept the license and add the HF_TOKEN to the environment:

os.environ["HF_TOKEN"] = config["HF_TOKEN"]

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