Instructions to use LaserNav/SophyAI-Mistral-7B-v3-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LaserNav/SophyAI-Mistral-7B-v3-GGUF with Adapters:

from adapters import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("undefined")
model.load_adapter("LaserNav/SophyAI-Mistral-7B-v3-GGUF", set_active=True)

llama-cpp-python

How to use LaserNav/SophyAI-Mistral-7B-v3-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LaserNav/SophyAI-Mistral-7B-v3-GGUF",
	filename="SophyAI-Mistral-7B-v3-Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LaserNav/SophyAI-Mistral-7B-v3-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LaserNav/SophyAI-Mistral-7B-v3-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 LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LaserNav/SophyAI-Mistral-7B-v3-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 LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use LaserNav/SophyAI-Mistral-7B-v3-GGUF with Ollama:
```
ollama run hf.co/LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M
```

Unsloth Studio new

How to use LaserNav/SophyAI-Mistral-7B-v3-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 LaserNav/SophyAI-Mistral-7B-v3-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 LaserNav/SophyAI-Mistral-7B-v3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LaserNav/SophyAI-Mistral-7B-v3-GGUF to start chatting

Docker Model Runner
How to use LaserNav/SophyAI-Mistral-7B-v3-GGUF with Docker Model Runner:
```
docker model run hf.co/LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M
```

Lemonade

How to use LaserNav/SophyAI-Mistral-7B-v3-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LaserNav/SophyAI-Mistral-7B-v3-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.SophyAI-Mistral-7B-v3-GGUF-Q4_K_M

List all available models

lemonade list

Model Card for Model ID

A preview model for support safety and security at work. Fine tuned model in italian language with italian rules

Model Details

This model derived from Mistral-7b has been fine-tuned with a dataset dedicated to the regulations governing safety at work developed by our AI Teams. The SofyAI patented platform is a digital twin framework for develop an AI supervisor for implement safety and security workflow at work. more info available at : https://www.lasernavigation.it This is a preview version of our SophyAI-LLM model the fine tuning did in Italian Language , so this early preview could don’t work in other language.

Developed by: [Laser Navigation srl]
Model type: [Fine Tuned Mistral]
Language(s) (NLP): [Italian]
License: [BSD]
Finetuned from model [optional]: [Mistral 7B]

Downloads last month: 14

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

Inference Providers NEW

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