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

Libraries

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

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

pipe = pipeline("text-generation", model="google/gemma-7b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

llama-cpp-python

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

# !pip install llama-cpp-python

from llama_cpp import Llama

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

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use google/gemma-7b-it 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-it
# Run inference directly in the terminal:
llama-cli -hf google/gemma-7b-it

Install from WinGet (Windows)

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

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-it
# Run inference directly in the terminal:
./llama-cli -hf google/gemma-7b-it

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-it
# Run inference directly in the terminal:
./build/bin/llama-cli -hf google/gemma-7b-it

Use Docker

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

LM Studio
Jan

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-7b-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-7b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use google/gemma-7b-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-7b-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-7b-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-7b-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-7b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

Unsloth Studio new

How to use google/gemma-7b-it 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-it 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-it 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-it to start chatting

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

ValueError: Trying to set a tensor of shape torch.Size([4096, 3072]) in "weight" (which has shape torch.Size([6291456, 1])), this look incorrect.

#81

by Subhasisdasgupta - opened Mar 25, 2024

Discussion

Subhasisdasgupta

Mar 25, 2024

•

edited Mar 25, 2024

I was trying to use langchain with HuggingFaceLLM wrapper to experiment with Gemma-7B model. In colab, the model worked fine but on my laptop it is giving the above-mentioned error. I am unable to debug it. My laptop has 6GB GPU RAM and 32 GB CPU RAM. The llm model was built with the following code:

quantization_config = BitsAndBytesConfig(load_in_4bit=True,
llm_int8_enable_fp32_cpu_offload=True,
bnb_4bit_use_double_quant=True)

llm = HuggingFaceLLM(
context_window=4096,
max_new_tokens=50,
generate_kwargs={"do_sample": False},
system_prompt=system_prompt,
query_wrapper_prompt=query_wrapper_prompt,
tokenizer_name="google/gemma-7b",
model_name="google/gemma-7b",
device_map="auto",
model_kwargs={"torch_dtype": torch.float16, "quantization_config": quantization_config}
)
It gave a warning: "Some parameters are on the meta device device because they were offloaded to the CPU". This is understandable. No such warning was there in Colab as Colab gives larger GPU memory.

I created the index and the queries as below:

query_engine = index.as_query_engine()
r = query_engine.query(query)

Then it gave the dimension mismatch error.

Please suggest how to get past this problem.

The installed packages are:

accelerate==0.28.0
aiohttp==3.9.3
aiosignal==1.3.1
annotated-types==0.6.0
anyio==4.3.0
asttokens==2.4.1
async-timeout==4.0.3
attrs==23.2.0
backcall==0.2.0
beautifulsoup4==4.12.3
bitsandbytes==0.43.0
bs4==0.0.2
certifi==2024.2.2
charset-normalizer==3.3.2
click==8.1.7
comm==0.2.2
dataclasses-json==0.6.4
debugpy==1.6.7
decorator==5.1.1
Deprecated==1.2.14
dirtyjson==1.0.8
distro==1.9.0
einops==0.7.0
entrypoints==0.4
exceptiongroup==1.2.0
executing==2.0.1
filelock==3.13.1
frozenlist==1.4.1
fsspec==2024.3.1
greenlet==3.0.3
h11==0.14.0
httpcore==1.0.4
httpx==0.27.0
huggingface-hub==0.20.3
idna==3.6
install==1.3.5
ipykernel==6.29.3
ipython==8.12.0
jedi==0.19.1
Jinja2==3.1.3
joblib==1.3.2
jsonpatch==1.33
jsonpointer==2.4
jupyter-client==7.3.4
jupyter_core==5.7.2
langchain==0.1.13
langchain-community==0.0.29
langchain-core==0.1.33
langchain-text-splitters==0.0.1
langsmith==0.1.31
llama-index==0.10.23
llama-index-agent-openai==0.1.7
llama-index-cli==0.1.11
llama-index-core==0.10.23.post1
llama-index-embeddings-huggingface==0.1.4
llama-index-embeddings-langchain==0.1.2
llama-index-embeddings-openai==0.1.7
llama-index-indices-managed-llama-cloud==0.1.5
llama-index-legacy==0.9.48
llama-index-llms-huggingface==0.1.4
llama-index-llms-openai==0.1.12
llama-index-multi-modal-llms-openai==0.1.4
llama-index-program-openai==0.1.4
llama-index-question-gen-openai==0.1.3
llama-index-readers-file==0.1.12
llama-index-readers-llama-parse==0.1.3
llama-parse==0.3.9
llamaindex-py-client==0.1.13
MarkupSafe==2.1.5
marshmallow==3.21.1
matplotlib-inline==0.1.6
mpmath==1.3.0
multidict==6.0.5
mypy-extensions==1.0.0
nest_asyncio==1.6.0
networkx==3.2.1
nltk==3.8.1
numpy==1.26.4
nvidia-cublas-cu12==12.1.3.1
nvidia-cuda-cupti-cu12==12.1.105
nvidia-cuda-nvrtc-cu12==12.1.105
nvidia-cuda-runtime-cu12==12.1.105
nvidia-cudnn-cu12==8.9.2.26
nvidia-cufft-cu12==11.0.2.54
nvidia-curand-cu12==10.3.2.106
nvidia-cusolver-cu12==11.4.5.107
nvidia-cusparse-cu12==12.1.0.106
nvidia-nccl-cu12==2.19.3
nvidia-nvjitlink-cu12==12.4.99
nvidia-nvtx-cu12==12.1.105
openai==1.14.2
orjson==3.9.15
packaging==23.2
pandas==2.2.1
parso==0.8.3
pexpect==4.9.0
pickleshare==0.7.5
pillow==10.2.0
pip==23.3.1
platformdirs==4.2.0
prompt-toolkit==3.0.42
psutil==5.9.0
ptyprocess==0.7.0
pure-eval==0.2.2
pydantic==2.6.4
pydantic_core==2.16.3
Pygments==2.17.2
PyMuPDF==1.24.0
PyMuPDFb==1.24.0
pypdf==4.1.0
python-dateutil==2.9.0
pytz==2024.1
PyYAML==6.0.1
pyzmq==25.1.2
regex==2023.12.25
requests==2.31.0
safetensors==0.4.2
scikit-learn==1.4.1.post1
scipy==1.12.0
sentence-transformers==2.6.0
setuptools==68.2.2
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SQLAlchemy==2.0.29
stack-data==0.6.2
striprtf==0.0.26
sympy==1.12
tenacity==8.2.3
threadpoolctl==3.4.0
tiktoken==0.6.0
tokenizers==0.15.2
torch==2.2.1
tornado==6.1
tqdm==4.66.2
traitlets==5.14.2
transformers==4.39.1
triton==2.2.0
typing_extensions==4.10.0
typing-inspect==0.9.0
tzdata==2024.1
urllib3==2.2.1
wcwidth==0.2.13
wheel==0.41.2
wrapt==1.16.0
yarl==1.9.4

Thanks in advance

Subhasis

lkv

Google org Aug 14, 2024

Hi @Subhasisdasgupta , The device_map="auto" setting automatically splits the model across available devices. However, if your GPU memory is limited (6GB), it might cause issues when layers are distributed in ways that cause tensor dimension mismatches. You can try explicitly setting the device_map to a simpler configuration.
device_map={"": "cpu"} to force CPU usage. Kindly try and let us know if the issue still persists. Thank you.

eshanc

Aug 20, 2025

hey @Subhasisdasgupta you might find Impulse AI (https://www.impulselabs.ai/) useful. we make it super easy to fine-tune and deploy open source models. hopefully you find it helpful! i know not relevant to your problem above but might be easier to use us to fine tune and deploy

docs: https://docs.impulselabs.ai/introduction
python sdk: https://pypi.org/project/impulse-api-sdk-python/

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