Instructions to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with PEFT:
```
Task type is invalid.
```

How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR",
	filename="Mina_AI_FLASH_LLM_DZ_AR_FR.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR
# Run inference directly in the terminal:
llama-cli -hf Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR
# Run inference directly in the terminal:
llama-cli -hf Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

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 Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR
# Run inference directly in the terminal:
./llama-cli -hf Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

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 Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

Use Docker

docker model run hf.co/Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

LM Studio
Jan

vLLM

How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

Ollama
How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with Ollama:
```
ollama run hf.co/Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR
```

Unsloth Studio

How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR 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 Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR 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 Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR to start chatting

How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

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": "Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with Docker Model Runner:
```
docker model run hf.co/Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR
```

Lemonade

How to use Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

Run and chat with the model

lemonade run user.Mina_AI_FLASH_LLM_DZ_AR-FR-{{QUANT_TAG}}

List all available models

lemonade list

Mina AI FLASH LLM AR-FR 🇩🇿

Mina AI est une intelligence artificielle algérienne.
Elle a été spécialement fine-tunée sur la base du puissant modèle structuré Qwen2.5 (7B) pour comprendre et générer le Darija algérien de manière naturelle et fluide.

🟢 Capacités Linguistiques

Je parle couramment :

🇩🇿 Le Darija algérien (dialecte local, vocabulaire urbain et traditionnel)
🇸🇦 L'Arabe classique (littéraire et MSA)
🇫🇷 Le Français

Je suis conçue pour assister, répondre aux questions, traduire, résumer et dialoguer en respectant activement le contexte culturel et linguistique algérien.

**Exemple d'interaction de lancement :

"Salam Mina, wech raki lyoum ? Kiraki m3a lkhedma ?"

⚙️ Détails Techniques

Créateur : Nasro
Base Model : Qwen/Qwen2.5-7B
Méthode d'entraînement : LoRA (Low-Rank Adaptation)
Format du poids : GGUF (Quantization Q4_K_M) - Optimisé pour l'inférence rapide sur des configurations matérielles légères (CPU/GPU)
Licence : Apache 2.0 (Open-Source et commercial-friendly)

💻 Comment m'utiliser localement ?

Ce modèle est fourni au format allégé et prêt à l'emploi gguf pour tourner à haute vitesse sur vos propres machines (PC Windows, Mac, Linux) via des logiciels comme LM Studio ou Ollama.

Téléchargez gratuitement l'application LM Studio.
Téléchargez le fichier Mina_AI_FLASH_LLM_DZ_AR_FR.gguf depuis l'onglet Files and versions de cette page.
Glissez le fichier dans votre dossier de modèles locaux de LM Studio.
Sélectionnez le modèle Mina-AI dans la liste déroulante et commencez à discuter en Darija !

Downloads last month: 48

GGUF

Model size

8B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for Nasro31/Mina_AI_FLASH_LLM_DZ_AR-FR

Base model

Qwen/Qwen2.5-7B

Adapter

(497)

this model