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

How long does this approval process take?

#10

by mitkox - opened Feb 21, 2024

Discussion

mitkox

Feb 21, 2024

How long does this approval process take?

mlabonne

Feb 21, 2024

Do you also see "Your request to access this repo has been successfully submitted, and is pending a review from the repo's authors." in the Files and versions tab, but you get a "We can't find that page." when you try to acknowledge the license in the model card?

mitkox

Feb 21, 2024

Yes exactly the same loop and can't access the files

nopainkiller

Feb 21, 2024

Do you also see "Your request to access this repo has been successfully submitted, and is pending a review from the repo's authors." in the Files and versions tab, but you get a "We can't find that page." when you try to acknowledge the license in the model card?

Was exactly staring at that lol

mlabonne

Feb 21, 2024

Okay cool, nothing we can do then let's wait and see :)

Kukedlc

Feb 21, 2024

•

edited Feb 21, 2024

Kaggle approvals take between one day to two. With Llama, it was the same; you accepted the consent on Kaggle and within hours, you were allowed access. Anyway, you can download from Kaggle upon accepting the license! As a plan B. (You select the version and next to "new notebook" download the model (+25GB gemma 7b).)

nopainkiller

Feb 21, 2024

Okay cool, nothing we can do then let's wait and see :)

I just figured it out, you need to click the consent on the model card page with a jump over license page on kaggle, then you could access the files

mlabonne

Feb 21, 2024

Just got accepted!

nopainkiller

Feb 21, 2024

Just got accepted!

I did a quick Q4_K_M of the Gemma-2B myself: https://huggingface.co/nopainkiller/Gemma-2B-GGUF/tree/main, it is not functioning with llama.cpp somehow with error "llama_model_load: error loading model: create_tensor: tensor 'output.weight' not found" (I ran with the latest pull). Hopefully your 7B-IT will have a successful one

osanseviero

Google org Feb 21, 2024

Hey all,we had a bug during the launch! You should get immediate access now after going through the accept flow.

osanseviero changed discussion status to closed Feb 21, 2024

postmasters

Google org Feb 21, 2024

Just got accepted!

I did a quick Q4_K_M of the Gemma-2B myself: https://huggingface.co/nopainkiller/Gemma-2B-GGUF/tree/main, it is not functioning with llama.cpp somehow with error "llama_model_load: error loading model: create_tensor: tensor 'output.weight' not found" (I ran with the latest pull). Hopefully your 7B-IT will have a successful one

This depends on how your conversion is done. Two things to make sure: 1) the GGUF arch must be gemma and 2) there is no output weight in this arch because it shares the same embedding weights as the input layer. The error you see suggests that the arch is likely not set / copied correctly by the converter.

nopainkiller

Feb 22, 2024

Just got accepted!

I did a quick Q4_K_M of the Gemma-2B myself: https://huggingface.co/nopainkiller/Gemma-2B-GGUF/tree/main, it is not functioning with llama.cpp somehow with error "llama_model_load: error loading model: create_tensor: tensor 'output.weight' not found" (I ran with the latest pull). Hopefully your 7B-IT will have a successful one

This depends on how your conversion is done. Two things to make sure: 1) the GGUF arch must be gemma and 2) there is no output weight in this arch because it shares the same embedding weights as the input layer. The error you see suggests that the arch is likely not set / copied correctly by the converter.

Thx !

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