Instructions to use Mattimax/DATA-AI_Chat_4_0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mattimax/DATA-AI_Chat_4_0.6B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Mattimax/DATA-AI_Chat_4_0.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mattimax/DATA-AI_Chat_4_0.6B")
model = AutoModelForCausalLM.from_pretrained("Mattimax/DATA-AI_Chat_4_0.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Mattimax/DATA-AI_Chat_4_0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mattimax/DATA-AI_Chat_4_0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mattimax/DATA-AI_Chat_4_0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Mattimax/DATA-AI_Chat_4_0.6B

SGLang

How to use Mattimax/DATA-AI_Chat_4_0.6B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Mattimax/DATA-AI_Chat_4_0.6B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mattimax/DATA-AI_Chat_4_0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Mattimax/DATA-AI_Chat_4_0.6B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mattimax/DATA-AI_Chat_4_0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Mattimax/DATA-AI_Chat_4_0.6B with Docker Model Runner:
```
docker model run hf.co/Mattimax/DATA-AI_Chat_4_0.6B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

🚀 DATA-AI_Chat_4_0.6B – Model Card

✅ Modello Maturo – Pronto per Applicazioni Reali Questo modello rappresenta un'evoluzione stabile della serie DATA-AI Chat, con capacità linguistiche più avanzate e migliori prestazioni generali.

✅ Production-Grade Model – Ready for Real Applications This model is a stable evolution of the DATA-AI Chat series, featuring improved language abilities and overall better performance.

🇮🇹 Descrizione del Modello

Mattimax/DATA-AI_Chat_4_0.6B è un modello linguistico multiuso sviluppato da M.INC., progettato per supportare conversazioni, assistenza automatizzata, e prototipi AI in ambienti produttivi leggeri. Basato su tecnologie raffinate rispetto alla versione Thinking_0.5B, questo modello sfrutta 0.6 miliardi di parametri, ottimizzati tramite tecniche avanzate di feedback umano e istruzione supervisionata.

Performance: migliorata e più fluida
Stabilità: elevata
Consigliato per: applicazioni reali, assistenza AI, automazione leggera

🇬🇧 Model Description

Mattimax/DATA-AI_Chat_4_0.6B is a general-purpose language model developed by M.INC., designed for lightweight AI applications such as conversational agents and automated assistance. It builds upon lessons from the earlier Thinking_0.5B prototype, scaling up to 0.6 billion parameters and integrating advanced instruction tuning and human-feedback methods.

Performance: enhanced and smoother
Stability: high
Recommended for: real-world usage, AI assistance, light automation

🎯 Obiettivo / Purpose

🇮🇹 Offrire un modello linguistico compatto ma efficace, adatto a scenari reali dove è necessaria una buona comprensione contestuale con risorse limitate. 🇬🇧 Deliver a compact yet effective language model suited for real-world scenarios requiring good contextual understanding with limited resources.

🗣️ Lingue Supportate / Supported Languages

🇮🇹 Italiano / Italian
🇬🇧 Inglese / English
🇪🇸 Spagnolo / Spanish
🇫🇷 Francese / French
➕ Supporto completo o parziale per oltre 30 lingue / Full or partial support for 30+ other languages

🏗️ Origine / Origin

Base model: Architettura proprietaria evoluta da DATA-AI_Chat_4_Thinking_0.5B
Sviluppato da / Developed by: Mattimax (M. Marzorati)
Organizzazione / Organization: M.INC.
Progetti correlati / Related Projects: DATANET – piattaforma AI conversazionale di nuova generazione

📌 Stato del Modello / Model Status

Caratteristica / Feature	Stato / Status
Tipo / Type	Stabile / Stable
Performance	Elevata / High
Stabilità / Stability	Garantita / Guaranteed
Utilizzo / Usage	Pronto per la produzione / Production-ready
Licenza / License	Apache 2.0

📥 Download

📦 Mattimax/DATA-AI_Chat_4_0.6B on Hugging Face

📝 Note Finali / Final Notes

🇮🇹 Con questa versione, la famiglia DATA-AI raggiunge una nuova maturità: un equilibrio tra leggerezza e intelligenza contestuale, pronto per essere integrato in sistemi reali.

🇬🇧 With this version, the DATA-AI family reaches a new maturity: a balance between lightness and contextual intelligence, ready to be integrated into real systems.