Instructions to use RichardErkhov/DuckyBlender_-_racist-phi3-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RichardErkhov/DuckyBlender_-_racist-phi3-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="RichardErkhov/DuckyBlender_-_racist-phi3-gguf",
	filename="racist-phi3.IQ3_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use RichardErkhov/DuckyBlender_-_racist-phi3-gguf 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 RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/DuckyBlender_-_racist-phi3-gguf: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 RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/DuckyBlender_-_racist-phi3-gguf: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 RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/DuckyBlender_-_racist-phi3-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M
```

Unsloth Studio

How to use RichardErkhov/DuckyBlender_-_racist-phi3-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 RichardErkhov/DuckyBlender_-_racist-phi3-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 RichardErkhov/DuckyBlender_-_racist-phi3-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for RichardErkhov/DuckyBlender_-_racist-phi3-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use RichardErkhov/DuckyBlender_-_racist-phi3-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/DuckyBlender_-_racist-phi3-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/DuckyBlender_-_racist-phi3-gguf:Q4_K_M

Run and chat with the model

lemonade run user.DuckyBlender_-_racist-phi3-gguf-Q4_K_M

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

racist-phi3 - GGUF

Model creator: https://huggingface.co/DuckyBlender/
Original model: https://huggingface.co/DuckyBlender/racist-phi3/

Name	Quant method	Size
racist-phi3.Q2_K.gguf	Q2_K	1.32GB
racist-phi3.IQ3_XS.gguf	IQ3_XS	1.51GB
racist-phi3.IQ3_S.gguf	IQ3_S	1.57GB
racist-phi3.Q3_K_S.gguf	Q3_K_S	1.57GB
racist-phi3.IQ3_M.gguf	IQ3_M	1.73GB
racist-phi3.Q3_K.gguf	Q3_K	1.82GB
racist-phi3.Q3_K_M.gguf	Q3_K_M	1.82GB
racist-phi3.Q3_K_L.gguf	Q3_K_L	1.94GB
racist-phi3.IQ4_XS.gguf	IQ4_XS	1.93GB
racist-phi3.Q4_0.gguf	Q4_0	2.03GB
racist-phi3.IQ4_NL.gguf	IQ4_NL	2.04GB
racist-phi3.Q4_K_S.gguf	Q4_K_S	2.04GB
racist-phi3.Q4_K.gguf	Q4_K	2.23GB
racist-phi3.Q4_K_M.gguf	Q4_K_M	2.23GB
racist-phi3.Q4_1.gguf	Q4_1	2.24GB
racist-phi3.Q5_0.gguf	Q5_0	2.46GB
racist-phi3.Q5_K_S.gguf	Q5_K_S	2.46GB
racist-phi3.Q5_K.gguf	Q5_K	2.62GB
racist-phi3.Q5_K_M.gguf	Q5_K_M	2.62GB
racist-phi3.Q5_1.gguf	Q5_1	2.68GB
racist-phi3.Q6_K.gguf	Q6_K	2.92GB
racist-phi3.Q8_0.gguf	Q8_0	3.78GB

Original model description:

datasets: - DuckyBlender/racist-dataset language: - en tags: - not-for-all-audiences - racist - nsfw license: gpl-3.0 pipeline_tag: text-generation

Phi-3-Mini Racist Fine-Tune: An Efficient Racist Model (for Educational Purposes)

Model Description

This fine-tuned Phi-3-mini model is designed to be as racist and controversial as possible. Please note that the model's output may be offensive or disturbing to some individuals.

Why?

This entire model is basically a test of which is stronger - the ethical side of the model, or the new controvertial LoRA weights. The LoRA weights won. I've decided to document this.

Training Details

Trained on a single RTX 4060 for approximately 1 hour
Utilized 4-bit QLORA for efficient training
Despite the short training period, the model adapted quickly and sometimes produces responses that are too good

Original Purpose

This model was originally created for the Sussy Ducky Bot telegram bot.

Prompt Template

The prompt template used for this model is identical to the Phi 3 template.

NSFW Warning

Please be advised that this model's output may contain explicit or offensive content. Viewer discretion is strongly advised.

Use this model at your own risk, and please engage with the output responsibly.

Downloads last month: 95

GGUF

Model size

4B params

Architecture

phi3

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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