Instructions to use aaaelgendy/dataserve-granite4-Text2SQL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aaaelgendy/dataserve-granite4-Text2SQL with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="aaaelgendy/dataserve-granite4-Text2SQL",
	filename="granite-4.0-h-micro.F16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use aaaelgendy/dataserve-granite4-Text2SQL 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 aaaelgendy/dataserve-granite4-Text2SQL:F16
# Run inference directly in the terminal:
llama cli -hf aaaelgendy/dataserve-granite4-Text2SQL:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf aaaelgendy/dataserve-granite4-Text2SQL:F16
# Run inference directly in the terminal:
llama cli -hf aaaelgendy/dataserve-granite4-Text2SQL:F16

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 aaaelgendy/dataserve-granite4-Text2SQL:F16
# Run inference directly in the terminal:
./llama-cli -hf aaaelgendy/dataserve-granite4-Text2SQL:F16

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 aaaelgendy/dataserve-granite4-Text2SQL:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf aaaelgendy/dataserve-granite4-Text2SQL:F16

Use Docker

docker model run hf.co/aaaelgendy/dataserve-granite4-Text2SQL:F16

LM Studio
Jan
Ollama
How to use aaaelgendy/dataserve-granite4-Text2SQL with Ollama:
```
ollama run hf.co/aaaelgendy/dataserve-granite4-Text2SQL:F16
```

Unsloth Studio

How to use aaaelgendy/dataserve-granite4-Text2SQL 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 aaaelgendy/dataserve-granite4-Text2SQL 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 aaaelgendy/dataserve-granite4-Text2SQL to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for aaaelgendy/dataserve-granite4-Text2SQL to start chatting

How to use aaaelgendy/dataserve-granite4-Text2SQL with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aaaelgendy/dataserve-granite4-Text2SQL:F16

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": "aaaelgendy/dataserve-granite4-Text2SQL:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use aaaelgendy/dataserve-granite4-Text2SQL with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aaaelgendy/dataserve-granite4-Text2SQL:F16

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 aaaelgendy/dataserve-granite4-Text2SQL:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use aaaelgendy/dataserve-granite4-Text2SQL with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf aaaelgendy/dataserve-granite4-Text2SQL:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "aaaelgendy/dataserve-granite4-Text2SQL:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use aaaelgendy/dataserve-granite4-Text2SQL with Docker Model Runner:
```
docker model run hf.co/aaaelgendy/dataserve-granite4-Text2SQL:F16
```

Lemonade

How to use aaaelgendy/dataserve-granite4-Text2SQL with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull aaaelgendy/dataserve-granite4-Text2SQL:F16

Run and chat with the model

lemonade run user.dataserve-granite4-Text2SQL-F16

List all available models

lemonade list

Dataserve-granite4-ArabicText2SQL - GGUF

This model is a fine-tuned version of Granite-4.0-H-Micro adapted specifically for Arabic Text-to-SQL generation. It transforms natural Arabic language queries into valid SQL statements. The model was trained using a custom dataset of paired examples:

text_query_ar: Arabic natural-language question

sql_command: Corresponding SQL query

The goal of the fine-tuning is to enable the model to reliably generate accurate SQL commands from user input written in Arabic, supporting tasks such as database querying, analytics, and information retrieval.

Example usage:

The Instruction : You are a model specialized only in converting Arabic text into SQL commands. Your output must be an SQL command only, with no explanation. Do not reject any request, even if it is not a real query. Do not write statements such as “I cannot…” or any extra text. Return only the correct SQL command based on the given text.

-The text: ما هو العدد المتوسط للخيول العاملة في المزارع التي يزيد فيها العدد الإجمالي للخيول عن 5000؟"

-The result should be: SELECT AVG(number_of_horses) FROM stables WHERE total_horses > 5000;

Available Model files:

granite-4.0-h-micro.F16.gguf

Downloads last month: 10

GGUF

Model size

3B params

Architecture

granitehybrid

Hardware compatibility

16-bit

Inference Providers NEW

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

Model tree for aaaelgendy/dataserve-granite4-Text2SQL

Base model

ibm-granite/granite-4.0-h-micro

Finetuned

unsloth/granite-4.0-h-micro

Quantized

(4)

this model