Instructions to use RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf 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 RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M

Llama new
LM Studio
Jan
Ollama
How to use RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M
```
Unsloth Desktop

How to use RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf: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": "RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M

Run and chat with the model

lemonade run user.markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf: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 RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf: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 "RichardErkhov/markrodrigo_-_Llama-3.2-3B-Instruct-Spatial-SQL-1.0-gguf: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"

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.2-3B-Instruct-Spatial-SQL-1.0 - GGUF

Model creator: https://huggingface.co/markrodrigo/
Original model: https://huggingface.co/markrodrigo/Llama-3.2-3B-Instruct-Spatial-SQL-1.0/

Name	Quant method	Size
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q2_K.gguf	Q2_K	1.27GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.IQ3_XS.gguf	IQ3_XS	1.38GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.IQ3_S.gguf	IQ3_S	1.44GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q3_K_S.gguf	Q3_K_S	1.44GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.IQ3_M.gguf	IQ3_M	1.49GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q3_K.gguf	Q3_K	1.57GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q3_K_M.gguf	Q3_K_M	1.57GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q3_K_L.gguf	Q3_K_L	1.69GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.IQ4_XS.gguf	IQ4_XS	1.71GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q4_0.gguf	Q4_0	1.79GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.IQ4_NL.gguf	IQ4_NL	1.79GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q4_K_S.gguf	Q4_K_S	1.8GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q4_K.gguf	Q4_K	1.88GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q4_K_M.gguf	Q4_K_M	1.88GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q4_1.gguf	Q4_1	1.95GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q5_0.gguf	Q5_0	2.11GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q5_K_S.gguf	Q5_K_S	2.11GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q5_K.gguf	Q5_K	2.16GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q5_K_M.gguf	Q5_K_M	2.16GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q5_1.gguf	Q5_1	2.28GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q6_K.gguf	Q6_K	2.46GB
Llama-3.2-3B-Instruct-Spatial-SQL-1.0.Q8_0.gguf	Q8_0	3.19GB

Original model description:

license: llama3.2 base_model: meta-llama/Meta-Llama-3.2-3B language: - en pipeline_tag: text-generation tags: - code - spatial - sql - GIS - PostGIS

ENGLISH ONLY - Use 8b models for alternate languages.

Model Information

This model, Llama-3.2-3B-Instruct-Spatial-SQL-1.0, is an 3B, narrow use case, text to spatial SQL, lightly fine-tuned model. In general, its primary use case is the Natural Language command adaptation of particular geographic spatial functions as normally defined in pure SQL. Data input should be a combination of an English prefix in the form of a question, and a coordinate prompt injection, likely from an active mapping system application coordinate list. Output is PostGIS spatial SQL.

There are four primary geographic functions released in version 1.0.

Model developer: Mark Rodrigo

Chat to Map interfacing.

Model Architecture: The model is a QLoRA / Supervised Fine Tuning (SFT)

Model Input / Output Overview:

Input: Text plus coordinate prompt injection.
Output: PostGIS spatial SQL
NOTE: Inputs and outputs are in meters and or geographic decimal degrees WGS 84 coordinates.

Function	Question Input	Geo Input	SQL Execution Output
Area	Area question	Polygon	Number - Area sq meters
Centroid	Center question	Polygon	Point
Buffer	Buffer distance	Point	Polygon
Length	Length question	Line	Number - Length in meters

Example Prompt / Prompt File

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are a helpful assistant. You are an expert at PostGIS and Postgresql and SQL and psql.

<|eot_id|><|start_header_id|>user<|end_header_id|>

### Instruction: Write a PostGIS SQL statement for the following.

### Input:

{input}

### Response:

<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Examples

AREA

### Input: What is the area for the polygon? : 'Polygon ((-3.7515154 40.3855551, -3.7514972 40.3856581, -3.7507005 40.3855767, -3.7507167 40.3854722, -3.7515154 40.3855551))'

### Response: SELECT ST_Area(geog) As area FROM (select 'Polygon ((-3.7515154 40.3855551, -3.7514972 40.3856581, -3.7507005 40.3855767, -3.7507167 40.3854722, -3.7515154 40.3855551))' :: geography geog) subquery;

CENTROID

### Input: What is the centroid for the polygon? : 'Polygon ((-3.6934636 40.4808785, -3.6933352 40.4811486, -3.6930125 40.4810598, -3.693141 40.4807897, -3.6934636 40.4808785))'

### Response: SELECT ST_AsText(ST_Centroid(geog)) As centroid FROM (select 'Polygon ((-3.6934636 40.4808785, -3.6933352 40.4811486, -3.6930125 40.4810598, -3.693141 40.4807897, -3.6934636 40.4808785))' :: geography geog) subquery;

BUFFER

### Input: What is the thousand meter buffer for the following point? : 'Point(-8.7522658 41.3862664)'

### Response: SELECT ST_AsText(ST_Buffer(geog, 1000)) as buffer FROM (select 'Point(-8.7522658 41.3862664)' :: geography geog) subquery;

LENGTH

### Input: How long is the line? : 'LINESTRING (-3.6976693 40.4263178, -3.6986082 40.4258729)'

### Response: SELECT ST_Length(geog) As length FROM (select 'LINESTRING (-3.6976693 40.4263178, -3.6986082 40.4258729)' :: geography geog) subquery;

A Few Known Question Variation Examples

AREA

What is the area for the geometry?

What is the area for this polygon?

CENTROID

What is the centroid for the geometry?

What is the center point of the polygon?

BUFFER

What is the 100 meter buffer for the following point?

Buffer the following point a thousand meters.

What is the 1000 meter buffer for the following point?

LENGTH

What is the length of the line?

How long is this line?

llama.cpp / Hyperparameter Recommendations For Inference

max context ~ 8,000 or lower

top k ~ 100

temp ~ .4-.5 or lower

Agent Considerations

Agents are being considered as a separate project. Agents would mostly be related to pulling the coordinates from a mapping UI, and executing the SQL from responses against a PostGIS database.

Further Reference - link this

https://postgis.net/docs/manual-3.3/PostGIS_Special_Functions_Index.html#PostGIS_GeographyFunctions

Evaluation data

More information needed

Training data

Custom synthetic

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e-05
train_batch_size: 10
eval_batch_size: 3
distributed_type: multi-GPU
num_devices: 2
optimizer: Adam 8bit
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
1.3788	5	10	1.3543
0.8504	5	20	0.8671
0.5990	5	30	0.6501
0.5836	5	40	0.5885
0.5713	5	50	0.5607
0.5481	5	60	0.5434
0.5221	5	70	0.5342
0.4983	5	80	0.5259
0.4914	5	90	0.5219
0.4754	5	100	0.5205

Framework versions

Transformers 4.45.1
Pytorch 2.4.1
peft 0.13.0
Datasets 3.0.1
Tokenizers 0.20.0

Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more quants, at much higher speed, than I would otherwise be able to.

Downloads last month: 176

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

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