Instructions to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF with PEFT:
```
Task type is invalid.
```

How to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF",
	filename="DATA-AI_Chat_2_0.5B-Intruct-Q8_0-V3.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0

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 Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0

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 Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0

Use Docker

docker model run hf.co/Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF with Ollama:
```
ollama run hf.co/Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0
```

Unsloth Studio new

How to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-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 Mattimax/DATA-AI_Chat_2_0.5B-Intruct-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 Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF to start chatting

Pi new

How to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0

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": "Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0

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 Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0

Run Hermes

hermes

Docker Model Runner
How to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF with Docker Model Runner:
```
docker model run hf.co/Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0
```

Lemonade

How to use Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mattimax/DATA-AI_Chat_2_0.5B-Intruct-GGUF:Q8_0

Run and chat with the model

lemonade run user.DATA-AI_Chat_2_0.5B-Intruct-GGUF-Q8_0

List all available models

lemonade list

Model Card for Mattimax/DATA-AI_Chat_2_0.5B-Intruct

Descrizione del Modello

Mattimax/DATA-AI_Chat_2_0.5B-Intruct è un modello di linguaggio conversazionale fine-tuned progettato per generare risposte interattive e coerenti in contesti di chat. È stato addestrato a partire dal modello base Qwen/Qwen2.5-0.5B-Intruct e successivamente fine-tuned sul dataset Mattimax/DATA-AI_Chat. Il modello è ideale per chatbot, assistenti virtuali e applicazioni di interazione testuale automatica.

Sviluppato da: Mattimax Team
Finanziato da: M.INC.
Condiviso da: Mattimax
Tipo di modello: Modello di linguaggio LLM (chatbot)
Lingua/e supportata/e: Italiano, Inglese
Licenza: Apache-2.0
Fine-tuned da: Qwen/Qwen2.5-0.5B-Intruct

Fonti del Modello

Repository: https://huggingface.co/Mattimax/DATA-AI_Chat_2_0.5B-Intruct

🔹 Chi ha creato DATA-AI?

DATA-AI è stato creato da *M.INC., un'azienda italiana fondata da *Mattimax (M. Marzorati).

🔹 Su quale architettura si basa DATA-AI?

Si basa su ELNS (Elaborazione del Linguaggio Naturale Semplice), un'innovativa tecnologia sviluppata da M.INC.

🔹 Quali altri progetti ha sviluppato M.INC.?

M.INC. ha sviluppato anche DATANET, un'app di chat avanzata basata su DATA-AI.

🔹 In quali lingue è addestrato il modello?

Attualmente, il dataset contiene informazioni in italiano, inglese, spagnolo e francese.

📥 Download e Utilizzo

Scarica il modello e il dataset dalla piattaforma Hugging Face e inizia subito a sperimentare con DATA-AI!

📢 Contatti e Supporto

Per ulteriori informazioni, domande o collaborazioni, contatta M.INC..

Downloads last month: 23

GGUF

Model size

0.5B params

Architecture

qwen2

Hardware compatibility

8-bit

Inference Providers NEW

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