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

Libraries

How to use andrijdavid/MeanGirl with Transformers:

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

pipe = pipeline("text-generation", model="andrijdavid/MeanGirl")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("andrijdavid/MeanGirl")
model = AutoModelForCausalLM.from_pretrained("andrijdavid/MeanGirl")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use andrijdavid/MeanGirl with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/andrijdavid/MeanGirl

SGLang

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

Docker Model Runner
How to use andrijdavid/MeanGirl with Docker Model Runner:
```
docker model run hf.co/andrijdavid/MeanGirl
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MeanGirl: A Dark Humor LLM based on LLaMA-2

Overview

MeanGirl is a cutting-edge language model, built upon the foundation of the LLaMA-2 architecture. It has been specially trained to generate content with a focus on dark humor. This model leverages a vast dataset of dark humor sources to understand and replicate the nuances and subtleties of this unique style of comedy. MeanGirl is designed for researchers, developers, and content creators who wish to explore the applications of dark humor in AI-driven projects.

Disclaimer

MeanGirl is designed to generate content that may include dark humor, which by its nature can be offensive to some audiences. The model may produce content that is NSFW, contains insults, or is otherwise provocative. It is intended for use by adults who are aware of the nature of the content it generates and is not suitable for all audiences or contexts.

Users are advised to exercise discretion and consider the potential impact and appropriateness of the content within their intended use case. The creators of MeanGirl do not endorse or condone the generated content and disclaim any liability for its use.

Downloads last month: 8

Safetensors

Model size

1B params

Tensor type

F32

Model tree for andrijdavid/MeanGirl

Quantizations

2 models