Instructions to use doss1232/CodeGemma-Offensive-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use doss1232/CodeGemma-Offensive-GGUF with Transformers:

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

pipe = pipeline("question-answering", model="doss1232/CodeGemma-Offensive-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("doss1232/CodeGemma-Offensive-GGUF", dtype="auto")

llama-cpp-python

How to use doss1232/CodeGemma-Offensive-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="doss1232/CodeGemma-Offensive-GGUF",
	filename="unsloth.F16.gguf",
)

llm.create_chat_completion(
	messages = "{\n    \"question\": \"What is my name?\",\n    \"context\": \"My name is Clara and I live in Berkeley.\"\n}"
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use doss1232/CodeGemma-Offensive-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf doss1232/CodeGemma-Offensive-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf doss1232/CodeGemma-Offensive-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf doss1232/CodeGemma-Offensive-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf doss1232/CodeGemma-Offensive-GGUF:F16

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 doss1232/CodeGemma-Offensive-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf doss1232/CodeGemma-Offensive-GGUF:F16

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 doss1232/CodeGemma-Offensive-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf doss1232/CodeGemma-Offensive-GGUF:F16

Use Docker

docker model run hf.co/doss1232/CodeGemma-Offensive-GGUF:F16

LM Studio
Jan
Ollama
How to use doss1232/CodeGemma-Offensive-GGUF with Ollama:
```
ollama run hf.co/doss1232/CodeGemma-Offensive-GGUF:F16
```

Unsloth Studio new

How to use doss1232/CodeGemma-Offensive-GGUF 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 doss1232/CodeGemma-Offensive-GGUF 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 doss1232/CodeGemma-Offensive-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for doss1232/CodeGemma-Offensive-GGUF to start chatting

Docker Model Runner
How to use doss1232/CodeGemma-Offensive-GGUF with Docker Model Runner:
```
docker model run hf.co/doss1232/CodeGemma-Offensive-GGUF:F16
```

Lemonade

How to use doss1232/CodeGemma-Offensive-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull doss1232/CodeGemma-Offensive-GGUF:F16

Run and chat with the model

lemonade run user.CodeGemma-Offensive-GGUF-F16

List all available models

lemonade list

Uploaded model

Developed by: doss1232
License: apache-2.0
Finetuned from model : unsloth/codegemma-7b-it-bnb-4bit

This gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.

Model info

This model is part of Offensive-Engine, a family of fine-tuned models for code-review, static-analysis and pentesting in general. It is a CodeGemma 9B model fine-tuned to understand code and detect vulnerabilities.

Memory requirement

This model can be used through lmstudio by searching the author's name and install it. It takes about 20GB to download and used 20GB RAM also.

Usage

Downloads last month: 81

GGUF

Model size

9B params

Architecture

gemma

Hardware compatibility

16-bit

Model tree for doss1232/CodeGemma-Offensive-GGUF

Base model

unsloth/codegemma-7b-it-bnb-4bit

Quantized

(3)

this model