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

Libraries

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

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

pipe = pipeline("text-generation", model="google/gemma-2b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

llama-cpp-python

How to use google/gemma-2b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="google/gemma-2b",
	filename="gemma-2b.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-2b 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-2b
# Run inference directly in the terminal:
llama-cli -hf google/gemma-2b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf google/gemma-2b
# Run inference directly in the terminal:
llama-cli -hf google/gemma-2b

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-2b
# Run inference directly in the terminal:
./llama-cli -hf google/gemma-2b

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-2b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf google/gemma-2b

Use Docker

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

LM Studio
Jan

vLLM

How to use google/gemma-2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-2b"
# 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-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use google/gemma-2b 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-2b" \
    --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-2b",
		"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-2b" \
        --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-2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use google/gemma-2b with Ollama:
```
ollama run hf.co/google/gemma-2b
```

Unsloth Studio new

How to use google/gemma-2b 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-2b 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-2b 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-2b to start chatting

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

Lemonade

How to use google/gemma-2b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull google/gemma-2b

Run and chat with the model

lemonade run user.gemma-2b-{{QUANT_TAG}}

List all available models

lemonade list

ImportError: Using `bitsandbytes` 8-bit quantization requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes

#29

by WQW - opened Mar 1, 2024

Discussion

WQW

Mar 1, 2024

•

edited Mar 1, 2024

Error:

as following
pip install accelerate bitsandbytes doesn't work

ImportError: Using `bitsandbytes` 8-bit quantization requires Accelerate: `pip install accelerate` and the latest version of bitsandbytes

Env info

Python            3.12.1
accelerate               0.27.2
bitsandbytes             0.42.0
torch                    2.2.1
tqdm                     4.65.0
transformers             4.38.2
trl                      0.7.11

Someone says we need to downgrade transformers library to version 4.30, on order to fix this error

However, GemmerTokenizer need to upgrade transformers to version 4.38 ...

ybelkada

Mar 4, 2024

Hi @WQW
Thanks for the issue, if you are using a jupyter notebook / google colab make sure to restart the kernel and re-install everything again. Also make sure to have access to a GPU device

WQW

Mar 4, 2024

Hi @WQW
Thanks for the issue, if you are using a jupyter notebook / google colab make sure to restart the kernel and re-install everything again. Also make sure to have access to a GPU device

I am running code on linux server terminal locally

ybelkada

Mar 4, 2024

Can you retry on a fresh new env? Also can you confirm you have access to a GPU device?

HONGMAOLIN

Mar 8, 2024

I also encountered the same issue

Chipiri

Mar 8, 2024

I am having the same issue. I am using Google Colab with an A100 GPU and have tried several versions of bitsandbytes, all >=4.1.3 since only this version supports the quantization method. I had to install version 0.4.2 on Google Colab, and that one worked.

aryachakraborty

Mar 10, 2024

@WQW @HONGMAOLIN I think if you are experimenting this locally. Accelerate requires GPU (Mandatory). without GPU accelerate won't work. You may try that on google colab free T4.

gitshiva

Mar 24, 2024

Hi @WQW
Thanks for the issue, if you are using a jupyter notebook / google colab make sure to restart the kernel and re-install everything again. Also make sure to have access to a GPU device

this worked for me! Thank you! (PS: Restarting kernel on Google CoLab!)

zeebrog

Mar 26, 2024

Happening for me on Windows(no GPU) with python 3.11 and:
accelerate 0.28.0
bitsandbytes 0.43.0
transformers 4.38.2

ybelkada

Apr 10, 2024

Hi @zeebrog ,
In order to use bnb you need to have access to a GPU

thepandapi

Apr 11, 2024

same issue on a mac m1

aryachakraborty

Apr 11, 2024

@thepandapi as far as I know Mac doesn't have a dedicated GPU. Please make sure if you are using the library locally you have a dedicated GPU.

ananu

May 18, 2024

I am having the same issue

packages installed with CUDA 11.8 -
torch - 2.3.0+cu118
llama-index - 0.10.37
llama-index-llms-huggingface - 0.2.0
transformers - 4.39.0
accelerate - 0.27.0
bitsandbytes - 0.43.1

harshitface2003

May 26, 2024

@ybelkada Thank you mate! It worked after restarting the jupyter notebook

BeastDevMoney

Jul 31, 2024

Hi everyone, there are news about this issue? I have the same issue In a windows machine with a dedicated GPU, a rtx 3060 of 20gbs.

lkv

Google org Jul 25, 2025

•

edited Jul 25, 2025

Hi , Sorry for the late response, BitsAndBytes 8-bit quantization requires the Accelerate library, which is not installed or an outdated version is being used, Ensure that accelerate is installed with pip install accelerate. and Update bitsandbytes to the latest version with pip install -i . and also use 4-bit quantization instead of 8-bit. It provides better performance, uses less memory, and is often more stable and better supported in recent library versions. Kindly try this version of bitsandbytes, all >=4.1.3 since only this version supports the quantization method.

Kindly try and let me know if issue is still persists. 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