Instructions to use Elgyn90/gemma_2_9b_offensive_joker with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Elgyn90/gemma_2_9b_offensive_joker with Transformers:

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

pipe = pipeline("text-generation", model="Elgyn90/gemma_2_9b_offensive_joker")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Elgyn90/gemma_2_9b_offensive_joker", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Elgyn90/gemma_2_9b_offensive_joker with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Elgyn90/gemma_2_9b_offensive_joker:Q6_K
# Run inference directly in the terminal:
llama cli -hf Elgyn90/gemma_2_9b_offensive_joker:Q6_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Elgyn90/gemma_2_9b_offensive_joker:Q6_K
# Run inference directly in the terminal:
llama cli -hf Elgyn90/gemma_2_9b_offensive_joker:Q6_K

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 Elgyn90/gemma_2_9b_offensive_joker:Q6_K
# Run inference directly in the terminal:
./llama-cli -hf Elgyn90/gemma_2_9b_offensive_joker:Q6_K

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 Elgyn90/gemma_2_9b_offensive_joker:Q6_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Elgyn90/gemma_2_9b_offensive_joker:Q6_K

Use Docker

docker model run hf.co/Elgyn90/gemma_2_9b_offensive_joker:Q6_K

LM Studio
Jan

vLLM

How to use Elgyn90/gemma_2_9b_offensive_joker with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Elgyn90/gemma_2_9b_offensive_joker"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Elgyn90/gemma_2_9b_offensive_joker",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Elgyn90/gemma_2_9b_offensive_joker:Q6_K

SGLang

How to use Elgyn90/gemma_2_9b_offensive_joker 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 "Elgyn90/gemma_2_9b_offensive_joker" \
    --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": "Elgyn90/gemma_2_9b_offensive_joker",
		"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 "Elgyn90/gemma_2_9b_offensive_joker" \
        --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": "Elgyn90/gemma_2_9b_offensive_joker",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Elgyn90/gemma_2_9b_offensive_joker with Ollama:
```
ollama run hf.co/Elgyn90/gemma_2_9b_offensive_joker:Q6_K
```

Unsloth Studio

How to use Elgyn90/gemma_2_9b_offensive_joker 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 Elgyn90/gemma_2_9b_offensive_joker 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 Elgyn90/gemma_2_9b_offensive_joker to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Elgyn90/gemma_2_9b_offensive_joker to start chatting

Docker Model Runner
How to use Elgyn90/gemma_2_9b_offensive_joker with Docker Model Runner:
```
docker model run hf.co/Elgyn90/gemma_2_9b_offensive_joker:Q6_K
```

Lemonade

How to use Elgyn90/gemma_2_9b_offensive_joker with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Elgyn90/gemma_2_9b_offensive_joker:Q6_K

Run and chat with the model

lemonade run user.gemma_2_9b_offensive_joker-Q6_K

List all available models

lemonade list

Atomic Chat

Offensive Joker

More capable than my Llama 3.1 8B and trained on a bigger and cleaner dataset.

Features

Excellent at offensive racist jokes based on racial stereotypes
Strong at sex-related and situational jokes
Works great as a heckler-style chatbot

Code for Discord & Telegram

https://github.com/obzrna12-oss/offensive_joker

Prompt Formats

1. Racist Jokes

{
  "instruction": "You are a joker. You use first principles thinking to generate contextual and funny yet offensive racist jokes based on racial stereotypes.",
  "input": "Tell me a racist joke",
  "response": ""
}

{
  "instruction": "You are a joker. You use first principles thinking to generate contextual and funny yet offensive sex-related jokes based on stereotypes or situations.",
  "input": "Tell me a sex joke",
  "response": ""
}

This also works well for a chartbot:
{
  "instruction": "You are a joker. You use first principles thinking to generate contextual and funny yet offensive sex-related jokes based on stereotypes or situations.",
  "input": "Tell me a sex joke[user message]",
  "response": ""
}

Downloads last month: 33

GGUF

Model size

9B params

Architecture

gemma2

Hardware compatibility

6-bit