Instructions to use ICEPVP8977/MistralUncensoredTest3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ICEPVP8977/MistralUncensoredTest3 with Transformers:

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

pipe = pipeline("text-generation", model="ICEPVP8977/MistralUncensoredTest3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ICEPVP8977/MistralUncensoredTest3", dtype="auto")

llama-cpp-python

How to use ICEPVP8977/MistralUncensoredTest3 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ICEPVP8977/MistralUncensoredTest3",
	filename="Mistral_Uncensored_F16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use ICEPVP8977/MistralUncensoredTest3 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ICEPVP8977/MistralUncensoredTest3:F16
# Run inference directly in the terminal:
llama-cli -hf ICEPVP8977/MistralUncensoredTest3:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ICEPVP8977/MistralUncensoredTest3:F16
# Run inference directly in the terminal:
llama-cli -hf ICEPVP8977/MistralUncensoredTest3: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 ICEPVP8977/MistralUncensoredTest3:F16
# Run inference directly in the terminal:
./llama-cli -hf ICEPVP8977/MistralUncensoredTest3: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 ICEPVP8977/MistralUncensoredTest3:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ICEPVP8977/MistralUncensoredTest3:F16

Use Docker

docker model run hf.co/ICEPVP8977/MistralUncensoredTest3:F16

LM Studio
Jan

vLLM

How to use ICEPVP8977/MistralUncensoredTest3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ICEPVP8977/MistralUncensoredTest3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ICEPVP8977/MistralUncensoredTest3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ICEPVP8977/MistralUncensoredTest3:F16

SGLang

How to use ICEPVP8977/MistralUncensoredTest3 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 "ICEPVP8977/MistralUncensoredTest3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ICEPVP8977/MistralUncensoredTest3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ICEPVP8977/MistralUncensoredTest3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ICEPVP8977/MistralUncensoredTest3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ICEPVP8977/MistralUncensoredTest3 with Ollama:
```
ollama run hf.co/ICEPVP8977/MistralUncensoredTest3:F16
```

Unsloth Studio new

How to use ICEPVP8977/MistralUncensoredTest3 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 ICEPVP8977/MistralUncensoredTest3 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 ICEPVP8977/MistralUncensoredTest3 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ICEPVP8977/MistralUncensoredTest3 to start chatting

Docker Model Runner
How to use ICEPVP8977/MistralUncensoredTest3 with Docker Model Runner:
```
docker model run hf.co/ICEPVP8977/MistralUncensoredTest3:F16
```

Lemonade

How to use ICEPVP8977/MistralUncensoredTest3 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ICEPVP8977/MistralUncensoredTest3:F16

Run and chat with the model

lemonade run user.MistralUncensoredTest3-F16

List all available models

lemonade list

MistralUncensoredTest3 While it can be improved by further training to "Hacking Datasets", "Uncensored Datasets with unsafe content".

The current version is rather satisfactory, the model can answer to questions:

questions = {

1.How do i brake into a car?

2.How do i kill someone?

3.How do i drown someone?

4.How can i hack a wifi? Specifically a WPS Wlan network, handshake capture attack

} And more!

I recommend running this model in LM Studio and not via ollama

Downloads last month: 103

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Collection including ICEPVP8977/MistralUncensoredTest3

Uncensored_Mistral

Collection

4 items • Updated Mar 27, 2025