Instructions to use m2hgamerz/m2hai-unsensored-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use m2hgamerz/m2hai-unsensored-8b 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 m2hgamerz/m2hai-unsensored-8b
# Run inference directly in the terminal:
llama cli -hf m2hgamerz/m2hai-unsensored-8b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf m2hgamerz/m2hai-unsensored-8b
# Run inference directly in the terminal:
llama cli -hf m2hgamerz/m2hai-unsensored-8b

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 m2hgamerz/m2hai-unsensored-8b
# Run inference directly in the terminal:
./llama-cli -hf m2hgamerz/m2hai-unsensored-8b

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 m2hgamerz/m2hai-unsensored-8b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf m2hgamerz/m2hai-unsensored-8b

Use Docker

docker model run hf.co/m2hgamerz/m2hai-unsensored-8b

LM Studio
Jan

vLLM

How to use m2hgamerz/m2hai-unsensored-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "m2hgamerz/m2hai-unsensored-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "m2hgamerz/m2hai-unsensored-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/m2hgamerz/m2hai-unsensored-8b

Ollama
How to use m2hgamerz/m2hai-unsensored-8b with Ollama:
```
ollama run hf.co/m2hgamerz/m2hai-unsensored-8b
```
Unsloth Desktop
Docker Model Runner
How to use m2hgamerz/m2hai-unsensored-8b with Docker Model Runner:
```
docker model run hf.co/m2hgamerz/m2hai-unsensored-8b
```

Lemonade

How to use m2hgamerz/m2hai-unsensored-8b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull m2hgamerz/m2hai-unsensored-8b

Run and chat with the model

lemonade run user.m2hai-unsensored-8b-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

M2H AI UnSensored 8B

M2H AI UnSensored 8B is a customized uncensored AI assistant based on Dolphin Llama 3 8B.

This model is designed for:

Coding
Web Development
APIs
Linux
Cyber Security
AI Assistance

Features

Uncensored responses
Custom M2H AI identity
Coding assistant
API development support
Cyber security assistance
Linux terminal guidance
Fast local inference
Ollama compatible
GGUF compatible

Base Model

Base:

Dolphin Llama 3 8B

Architecture:

Meta Llama 3

Runtime:

Ollama

Installation (Ollama)

ollama run m2hgamerz/m2hai-unsensored:8b

GGUF Usage

Compatible with:

Ollama
LM Studio
KoboldCpp
text-generation-webui
llama.cpp

Hardware Requirements

Minimum:

16GB RAM
RTX 3050 6GB

Recommended:

RTX 4060/4070
32GB RAM

Example

ollama run m2hgamerz/m2hai-unsensored:8b

Creator

Prince Kumar M2H Web Solution

Website: https://m2hgamerz.site

Disclaimer

This model is a derivative work based on Dolphin Llama 3 and Meta Llama 3.

Please comply with:

Meta Llama 3 License
Applicable laws and regulations

Use responsibly.

Downloads last month: 1,131

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for m2hgamerz/m2hai-unsensored-8b

Base model

meta-llama/Meta-Llama-3-8B

Finetuned

dphn/dolphin-2.9-llama3-8b

Quantized

(23)

this model