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

Libraries

How to use Dasuperhub/DA with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Dasuperhub/DA",
	filename="DA-v3-Q4_K_M.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 Dasuperhub/DA with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Dasuperhub/DA:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Dasuperhub/DA:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Dasuperhub/DA:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Dasuperhub/DA: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 Dasuperhub/DA:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Dasuperhub/DA: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 Dasuperhub/DA:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Dasuperhub/DA:Q4_K_M

Use Docker

docker model run hf.co/Dasuperhub/DA:Q4_K_M

LM Studio
Jan

vLLM

How to use Dasuperhub/DA with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Dasuperhub/DA:Q4_K_M

Ollama
How to use Dasuperhub/DA with Ollama:
```
ollama run hf.co/Dasuperhub/DA:Q4_K_M
```

Unsloth Studio new

How to use Dasuperhub/DA 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 Dasuperhub/DA 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 Dasuperhub/DA to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use Dasuperhub/DA with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Dasuperhub/DA:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DA"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Dasuperhub/DA with Docker Model Runner:
```
docker model run hf.co/Dasuperhub/DA:Q4_K_M
```

Lemonade

How to use Dasuperhub/DA with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Dasuperhub/DA:Q4_K_M

Run and chat with the model

lemonade run user.DA-Q4_K_M

List all available models

lemonade list

DA — Guinea's AI

DA is a fine-tuned 0.6B language model that speaks Soussou (Susu), a West African language spoken by ~3 million people in Guinea, Sierra Leone, and Guinea-Bissau.

What is DA?

DA is the first AI model that natively speaks Soussou. Not through translation APIs — the language lives in the weights.

User: Qui es-tu?
DA: N tan Guinius, DA AI guineen. Mu fe di i bere?

Model Details

Property	Value
Base Model	Qwen3-0.6B
Method	QLoRA (r=16, alpha=16)
Training Data	17,438 ChatML examples
Languages	Soussou, French, English
Format	GGUF Q4_K_M
Size	379 MB
Context	2048 tokens
Final Loss	0.85-0.94

Why DA?

Offline: Runs on $100 phones with no internet
Free: No API keys, no monthly costs
Native: Soussou in the weights, not a wrapper
Small: 379MB GGUF — fits anywhere

Usage

With llama.cpp

./llama-cli --model DA-v3-Q4_K_M.gguf -p "Translate to Soussou: Good morning"

With Ollama

ollama create da -f Modelfile
ollama run da

Training Data

17,438 examples covering:

Soussou-French-English translations (GATITOS + custom pairs)
Soussou Bible text
Grammar and morphology
Conversational Soussou
Cultural context

Built by

DASH — Diop Abdoul Aziz | Guinea "Be the Best amongst the Bests — With Care and Love"

Part of the Guinius ecosystem.

Downloads last month: 14

GGUF

Model size

0.6B params

Architecture

qwen3

Hardware compatibility

4-bit

Model tree for Dasuperhub/DA

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Quantized

(297)

this model