Instructions to use north/north-mistral-7b-ggml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use north/north-mistral-7b-ggml with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="north/north-mistral-7b-ggml",
	filename="north-mistral-v0.2.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use north/north-mistral-7b-ggml 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 north/north-mistral-7b-ggml
# Run inference directly in the terminal:
llama cli -hf north/north-mistral-7b-ggml

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf north/north-mistral-7b-ggml
# Run inference directly in the terminal:
llama cli -hf north/north-mistral-7b-ggml

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 north/north-mistral-7b-ggml
# Run inference directly in the terminal:
./llama-cli -hf north/north-mistral-7b-ggml

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 north/north-mistral-7b-ggml
# Run inference directly in the terminal:
./build/bin/llama-cli -hf north/north-mistral-7b-ggml

Use Docker

docker model run hf.co/north/north-mistral-7b-ggml

LM Studio
Jan
Ollama
How to use north/north-mistral-7b-ggml with Ollama:
```
ollama run hf.co/north/north-mistral-7b-ggml
```

Unsloth Studio

How to use north/north-mistral-7b-ggml 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 north/north-mistral-7b-ggml 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 north/north-mistral-7b-ggml to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for north/north-mistral-7b-ggml to start chatting

Atomic Chat new
Docker Model Runner
How to use north/north-mistral-7b-ggml with Docker Model Runner:
```
docker model run hf.co/north/north-mistral-7b-ggml
```

Lemonade

How to use north/north-mistral-7b-ggml with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull north/north-mistral-7b-ggml

Run and chat with the model

lemonade run user.north-mistral-7b-ggml-{{QUANT_TAG}}

List all available models

lemonade list

Model Card: North Mistral 7B - GGML

Model Overview

The North Mistral 7B is part of a series of research experiements into creating Scandinavian LLMs. The current versions are pretrained only, so they will have to be finetuned before used. This repo provides experiemental GGML-versions of these models.

Model Architecture

North Mistral 7B is based on the Mistral architecture, renowned for its effectiveness in capturing complex patterns in large datasets. It utilizes a multi-layer transformer decoder structure.

version	checkpoint	val_loss
v0.1	40k	1.449

Training Data

The model was trained on a diverse dataset primarily in English, Swedish, Danish and Norwegian. A complete datacard will be published later.

Intended Use

This model is intended for developers and researchers only. It is particularly suited for applications requiring understanding and generating human-like text, including conversational agents, content generation tools, and automated translation services.

Limitations

The model will exhibit biases present in the training data.
Performance can vary significantly depending on the specificity of the task and the nature of the input data.
High computational requirements for inference may limit deployment on low-resource devices.

Ethical Considerations

Users are encouraged to evaluate the model carefully in controlled environments before deploying it in critical applications. Ethical use guidelines should be followed to prevent misuse of the model's capabilities, particularly in sensitive contexts.

Licensing

North Mistral 7B is released under the MIT Public License, which allows for both academic and commercial use.

Downloads last month: 1

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

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