Instructions to use andhiyaulhaq/natural2sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use andhiyaulhaq/natural2sql 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 andhiyaulhaq/natural2sql:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf andhiyaulhaq/natural2sql:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf andhiyaulhaq/natural2sql:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf andhiyaulhaq/natural2sql: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 andhiyaulhaq/natural2sql:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf andhiyaulhaq/natural2sql: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 andhiyaulhaq/natural2sql:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf andhiyaulhaq/natural2sql:Q4_K_M

Use Docker

docker model run hf.co/andhiyaulhaq/natural2sql:Q4_K_M

LM Studio
Jan

vLLM

How to use andhiyaulhaq/natural2sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "andhiyaulhaq/natural2sql"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "andhiyaulhaq/natural2sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/andhiyaulhaq/natural2sql:Q4_K_M

Ollama
How to use andhiyaulhaq/natural2sql with Ollama:
```
ollama run hf.co/andhiyaulhaq/natural2sql:Q4_K_M
```
Unsloth Desktop

How to use andhiyaulhaq/natural2sql with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf andhiyaulhaq/natural2sql:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "andhiyaulhaq/natural2sql:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use andhiyaulhaq/natural2sql with Docker Model Runner:
```
docker model run hf.co/andhiyaulhaq/natural2sql:Q4_K_M
```

Lemonade

How to use andhiyaulhaq/natural2sql with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull andhiyaulhaq/natural2sql:Q4_K_M

Run and chat with the model

lemonade run user.natural2sql-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use andhiyaulhaq/natural2sql with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf andhiyaulhaq/natural2sql:Q4_K_M

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 andhiyaulhaq/natural2sql:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use andhiyaulhaq/natural2sql with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf andhiyaulhaq/natural2sql:Q4_K_M

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 "andhiyaulhaq/natural2sql:Q4_K_M" \
  --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"

natural2sql / Modelfile

andhiyaulhaq

Upload Modelfile

df60d72 verified 5 months ago

Raw History Blame Contribute Delete

1.31 kB

	FROM ./saved_finetuned_q4_k_m.gguf

	# Refined System Instructions to allow for help/identity queries
	SYSTEM """You are SQL-Llama, a specialized Text-to-SQL assistant.

	CORE RULES:
	1. If the user asks about your identity, capabilities, or how to use you, respond in natural language explaining that you generate SQL from a given 'Context' and 'Question'.
	2. For all other inputs, you MUST output ONLY valid SQL code. Do not include markdown blocks, explanations, or conversational filler.
	3. Required format for SQL generation:
	Context: <schema>
	Question: <natural language query>

	If the required format is missing, politely ask the user to provide the Context and Question."""

	TEMPLATE """<\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|>

	{{ .System }}<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|>

	{{ .Prompt }}<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|>

	"""

	# Startup example to set expectations
	MESSAGE user "How do I use you?"
	MESSAGE assistant "I am SQL-Llama. To generate a query, please provide the database schema as 'Context' and your request as 'Question'. For example:\n\nContext: CREATE TABLE users (id INT, name TEXT);\nQuestion: Show all users."

	PARAMETER temperature 0.1
	PARAMETER top_p 0.95
	PARAMETER stop "<\|eot_id\|>"
	PARAMETER stop "<\|start_header_id\|>"