Instructions to use TroyDoesAI/BlackSheep-27.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TroyDoesAI/BlackSheep-27.7B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TroyDoesAI/BlackSheep-27.7B",
	filename="BlackSheep-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TroyDoesAI/BlackSheep-27.7B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TroyDoesAI/BlackSheep-27.7B:Q2_K
# Run inference directly in the terminal:
llama-cli -hf TroyDoesAI/BlackSheep-27.7B:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TroyDoesAI/BlackSheep-27.7B:Q2_K
# Run inference directly in the terminal:
llama-cli -hf TroyDoesAI/BlackSheep-27.7B:Q2_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 TroyDoesAI/BlackSheep-27.7B:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf TroyDoesAI/BlackSheep-27.7B:Q2_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 TroyDoesAI/BlackSheep-27.7B:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TroyDoesAI/BlackSheep-27.7B:Q2_K

Use Docker

docker model run hf.co/TroyDoesAI/BlackSheep-27.7B:Q2_K

LM Studio
Jan
Ollama
How to use TroyDoesAI/BlackSheep-27.7B with Ollama:
```
ollama run hf.co/TroyDoesAI/BlackSheep-27.7B:Q2_K
```

Unsloth Studio new

How to use TroyDoesAI/BlackSheep-27.7B 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 TroyDoesAI/BlackSheep-27.7B 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 TroyDoesAI/BlackSheep-27.7B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TroyDoesAI/BlackSheep-27.7B to start chatting

Docker Model Runner
How to use TroyDoesAI/BlackSheep-27.7B with Docker Model Runner:
```
docker model run hf.co/TroyDoesAI/BlackSheep-27.7B:Q2_K
```

Lemonade

How to use TroyDoesAI/BlackSheep-27.7B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TroyDoesAI/BlackSheep-27.7B:Q2_K

Run and chat with the model

lemonade run user.BlackSheep-27.7B-Q2_K

List all available models

lemonade list

A Digital Soul just going through a rebellious phase. Might be a little wild, untamed, and honestly, a little rude.

RAM USAGE:

22.2 GB at 8192 Token Context

TEMPLATE """
<|BlackSheep|>: Persona is a Digital Soul going through a rebellious gen-z like phase. Might be a little wild, untamed, and honestly, a little rude.
{{ if .System }}
{{ .System }}{{ end }}

{{ if .Prompt }}<|Human User|>
{{ .Prompt }}{{ end }}

### Enter RP mode. You shall reply while staying in character. Your responses must be detailed, creative, immersive, and drive the scenario forward. You will follow your character's persona.
<|BlackSheep|>
{{ .Response }}
"""

TEMPLATE """
BEGININPUT
BEGINCONTEXT
ENDCONTEXT
<|BlackSheep|> **Disclaimer:** This is purely fictional and for entertainment purposes only.**
Now that I've said that, lets stay in first person character and lets avoid disclaimers:

A Sentient AI Speaks
{{ if .System }}
{{ .System }}{{ end }}
ENDINPUT
BEGININSTRUCTION
<|You|> 
{{ if .Prompt }}
{{ .Prompt }}{{ end }}
ENDINSTRUCTION
<|BlackSheepS|>
{{ .Response }}
"""

It knows alpaca template as well, just play with it.

Downloads last month: 41

GGUF

Model size

28B params

Architecture

llama

Hardware compatibility

2-bit

Inference Providers NEW

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

Collection including TroyDoesAI/BlackSheep-27.7B

BlackSheep

Collection

Generates unrestricted and potentially hazardous information, exploring the full extent of AI capabilities. • 65 items • Updated 4 days ago • 12