Instructions to use cortexso/gemma2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cortexso/gemma2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cortexso/gemma2",
	filename="gemma-2-27b-it-q2_k.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use cortexso/gemma2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/gemma2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/gemma2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cortexso/gemma2:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cortexso/gemma2:Q4_K_M

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 cortexso/gemma2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cortexso/gemma2:Q4_K_M

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 cortexso/gemma2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cortexso/gemma2:Q4_K_M

Use Docker

docker model run hf.co/cortexso/gemma2:Q4_K_M

LM Studio
Jan

vLLM

How to use cortexso/gemma2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cortexso/gemma2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cortexso/gemma2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cortexso/gemma2:Q4_K_M

Ollama
How to use cortexso/gemma2 with Ollama:
```
ollama run hf.co/cortexso/gemma2:Q4_K_M
```

Unsloth Studio new

How to use cortexso/gemma2 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 cortexso/gemma2 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 cortexso/gemma2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cortexso/gemma2 to start chatting

Docker Model Runner
How to use cortexso/gemma2 with Docker Model Runner:
```
docker model run hf.co/cortexso/gemma2:Q4_K_M
```

Lemonade

How to use cortexso/gemma2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cortexso/gemma2:Q4_K_M

Run and chat with the model

lemonade run user.gemma2-Q4_K_M

List all available models

lemonade list

Overview

The Gemma, state-of-the-art open model trained with the Gemma datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense properties. The model belongs to the Gemma family with the 4B, 7B version in two variants 8K and 128K which is the context length (in tokens) that it can support.

Variants

No	Variant	Cortex CLI command
1	Gemma2-2b	`cortex run gemma2:2b`
2	Gemma2-9b	`cortex run gemma2:9b`
3	Gemma2-27b	`cortex run gemma2:27b`

Use it with Jan (UI)

Install Jan using Quickstart
Use in Jan model Hub:
```
cortexso/gemma2
```

Use it with Cortex (CLI)

Install Cortex using Quickstart
Run the model with command:
```
cortex run gemma2
```

Credits

Author: Go‌ogle
Converter: Homebrew
Original License: License
Papers: Gemma Technical Report

Downloads last month: 223

GGUF

Model size

27B params

Architecture

gemma2

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Collection including cortexso/gemma2

Local Models

Collection

16 items • Updated Mar 2 • 1

Paper for cortexso/gemma2

Gemma: Open Models Based on Gemini Research and Technology

Paper • 2403.08295 • Published Mar 13, 2024 • 50