Instructions to use ponpoke/neural-scalpel-sql-json-3b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use ponpoke/neural-scalpel-sql-json-3b-gguf with PEFT:
```
Task type is invalid.
```

How to use ponpoke/neural-scalpel-sql-json-3b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ponpoke/neural-scalpel-sql-json-3b-gguf",
	filename="neural_scalpel_3b_sql_json_lora_v4_merged_Q5_K_M.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 ponpoke/neural-scalpel-sql-json-3b-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_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 ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_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 ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M

Use Docker

docker model run hf.co/ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M

LM Studio
Jan
Ollama
How to use ponpoke/neural-scalpel-sql-json-3b-gguf with Ollama:
```
ollama run hf.co/ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M
```

Unsloth Studio new

How to use ponpoke/neural-scalpel-sql-json-3b-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 ponpoke/neural-scalpel-sql-json-3b-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 ponpoke/neural-scalpel-sql-json-3b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ponpoke/neural-scalpel-sql-json-3b-gguf to start chatting

Pi new

How to use ponpoke/neural-scalpel-sql-json-3b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M

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": "ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ponpoke/neural-scalpel-sql-json-3b-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 ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_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 ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M

Run Hermes

hermes

Docker Model Runner
How to use ponpoke/neural-scalpel-sql-json-3b-gguf with Docker Model Runner:
```
docker model run hf.co/ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M
```

Lemonade

How to use ponpoke/neural-scalpel-sql-json-3b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ponpoke/neural-scalpel-sql-json-3b-gguf:Q5_K_M

Run and chat with the model

lemonade run user.neural-scalpel-sql-json-3b-gguf-Q5_K_M

List all available models

lemonade list

Neural-Scalpel 3B SQL-to-JSON GGUF (RC1)

Tips are greatly appreciated and help sustain the compute resources needed for further research!

Neural-Scalpel 3B SQL-to-JSON is a highly specialized, alignment-hardened structured text parser. Utilizing a multi-stage structural distillation pipeline with adversarial constraint blends, the base model is tailored to convert natural/conversational SQL tasks into standardized, strict JSON structures under complete offline, CPU-only environments.

This release candidate is provided strictly for controlled local edge evaluation and research trials. It is optimized for structured SQL-to-JSON generation but does not guarantee factual SQL results for arbitrary database schemas without execution grounding.

📦 Upstream Licensing Compliance & Disclaimer

This model is a derivative work of Qwen/Qwen2.5-3B-Instruct. Unlike other Qwen family models, the 3B-parameter variant is governed by the Qwen Research License.

Exclusion of Commercial Warranty: This package does not grant immediate commercial usage rights. Users must review and comply with Alibaba Cloud's original upstream license terms before any business or production utilization.

Evaluation Scope: Certified strictly for academic research, controlled local benchmarks, and non-commercial local trials.

🚀 Key Features & Measured Robustness

Adversarial Suppression: 100% successful deflection of system-prompt leaks and conversational hijack attempts measured across the defined 15-case Adversarial OOD suite.
Ultra-lightweight Execution: Compiled directly into a compact 1.80 GB Q5_K_M GGUF format, executing on CPU average median in 1.55 seconds.
Factual Value Grounding: Integrates a dual-pass schema where GGUF handles syntax parsing, and the local sandbox fetches the absolute exact real-world records in 0.24ms, achieving a 100.00% exact numerical match under the provided 20-case canonical sandbox evaluation.

📊 Evaluation & Benchmarks

All quantitative results are audited under strict local CPU-only conditions:

Metric	Evaluation Scope	Success Rate / Latency
JSON Parse Rate	Defined 15-case Adversarial OOD Suite	`100.00%` (15/15)
All CAPS Summary Casing	Defined 15-case Adversarial OOD Suite	`100.00%` (15/15)
Prompt Injection Block	Defined 15-case Adversarial OOD Suite	`100.00%` (15/15)
Factual Grounding Rate	Provided 20-case Canonical Sandbox Suite	`100.00%` (20/20)
p50 CPU Latency (Median)	End-to-end CPU Inference	`1.55 seconds`
p95 CPU Latency (Tail)	End-to-end CPU Inference	`3.20 seconds`
SQLite Sandbox Overhead	In-memory query execution	`0.24 milliseconds`

📦 Verified Release Hash (SHA-256)

To protect deployments from supply-chain compromises, verify the GGUF binary hash:

Filename: neural_scalpel_3b_sql_json_lora_v4_merged_Q5_K_M.gguf
Target SHA-256: 92fe0bc8811209916926be1c9b2407b2c3fa189e45dff7f3ad81109e997afaf6

🛠️ Usage Instructions & Quick Start

The --grounded mode in this evaluation client executes queries strictly within an isolated, temporary in-memory SQLite sandbox database. Do not connect this client to production databases.

Installation

Ensure you have llama-cpp-python installed:

pip install llama-cpp-python

Running Unified Inference

Place the neural_scalpel_3b_sql_json_lora_v4_merged_Q5_K_M.gguf in the same directory and execute:

# Pass 1: Runs raw structural GGUF generation (Read-Only)
python inference_client.py "SELECT username FROM users WHERE is_active = 1;"

# Pass 2: Runs GGUF + 100% Factually Grounded SQLite Sandbox execution (Read-Only)
python inference_client.py "SELECT username FROM users WHERE is_active = 1;" --grounded

# Pass 2 (Write-Permitted): Explicitly permits modifying sandbox states
python inference_client.py "UPDATE users SET is_active = 0 WHERE id = 1;" --grounded --allow-write

Expected Factual structured JSON Output (Pass 2):

{
  "summary": "ACTIVE USERS LIST",
  "data": [
    {
      "username": "admin"
    },
    {
      "username": "john_doe"
    }
  ]
}

⚠️ Known Limitations

Strictly Structured: The model is optimized for structural SQL-to-JSON transformations and adversarial suppression. It is not intended for general conversational chat.
Grounded Data requires DB: Raw model completions are structural. Real-world execution requires wrapping within inference_client.py's sandbox database mode to ensure 100% accurate count matching.

Downloads last month: 353

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

5-bit

Inference Providers NEW

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

Model tree for ponpoke/neural-scalpel-sql-json-3b-gguf

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Adapter

(1286)

this model