Instructions to use c2p-cmd/google_gemma_guff with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use c2p-cmd/google_gemma_guff with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="c2p-cmd/google_gemma_guff",
	filename="gemma_snapshot/gemma-2b-it.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use c2p-cmd/google_gemma_guff with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf c2p-cmd/google_gemma_guff
# Run inference directly in the terminal:
llama-cli -hf c2p-cmd/google_gemma_guff

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf c2p-cmd/google_gemma_guff
# Run inference directly in the terminal:
llama-cli -hf c2p-cmd/google_gemma_guff

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 c2p-cmd/google_gemma_guff
# Run inference directly in the terminal:
./llama-cli -hf c2p-cmd/google_gemma_guff

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 c2p-cmd/google_gemma_guff
# Run inference directly in the terminal:
./build/bin/llama-cli -hf c2p-cmd/google_gemma_guff

Use Docker

docker model run hf.co/c2p-cmd/google_gemma_guff

LM Studio
Jan
Ollama
How to use c2p-cmd/google_gemma_guff with Ollama:
```
ollama run hf.co/c2p-cmd/google_gemma_guff
```

Unsloth Studio new

How to use c2p-cmd/google_gemma_guff 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 c2p-cmd/google_gemma_guff 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 c2p-cmd/google_gemma_guff to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for c2p-cmd/google_gemma_guff to start chatting

Docker Model Runner
How to use c2p-cmd/google_gemma_guff with Docker Model Runner:
```
docker model run hf.co/c2p-cmd/google_gemma_guff
```

Lemonade

How to use c2p-cmd/google_gemma_guff with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull c2p-cmd/google_gemma_guff

Run and chat with the model

lemonade run user.google_gemma_guff-{{QUANT_TAG}}

List all available models

lemonade list

Gemma Model Card

Model Page: Gemma

This model card corresponds to the 2B and 7B Instruct versions of the Gemma model's Guff.

Terms of Use: Terms

Description

Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.

Model Usage

Since this is a guff, it can be run locally using

Ollama
Llama.cpp
LM Studio
And Many More
I have provided GemmaModelFile that can be used with ollama by:

Download the model:

pip install huggingface_hub
from huggingface_hub import hf_hub_download

model_id="c2p-cmd/google_gemma_guff"
hf_hub_download(repo_id=model_id, local_dir="gemma_snapshot", local_dir_use_symlinks=False, filename="gemma_snapshot/gemma-2b-it.gguf")

Load the model file to ollama
```
ollama create gemma -f GemmaModelFile
```
You change the model name based on needs

Downloads last month: 17

GGUF

Model size

3B params

Architecture

gemma

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support