Hugging Face's logo

markrodrigo
/
Llama-3.2-1B-Instruct-Spatial-SQL-1.0

Text Generation
Safetensors
English
llama
code
spatial
sql
GIS
PostGIS
conversational
Model card Files Community
Llama-3.2-1B-Instruct-Spatial-SQL-1.0 / README.md
markrodrigo's picture
markrodrigo
Update README.md
662adad verified
preview code
|
raw
history blame contribute delete
6.43 kB
metadata
license: llama3.2
base_model: meta-llama/Meta-Llama-3.2-1B
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-3.2-1B-Instruct-Spatial-SQL-1.0, is an 1B, 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

Github: https://github.com/mprodrigo/spatialsql

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 or lower

temp ~ .4-.7 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: 20

Training results

Training Loss Epoch Step Validation Loss
1.9106 20 10 1.9183
1.1674 20 20 1.1710
0.7446 20 30 0.7589
0.6143 20 40 0.6220
0.5773 20 50 0.5695
0.5328 20 60 0.5334
0.5146 20 70 0.5096
0.4895 20 80 0.4925
0.4893 20 90 0.4772
0.4710 20 100 0.4612
0.4572 20 110 0.4438
0.4358 20 120 0.4233
0.4002 20 130 0.4014
0.3812 20 140 0.3768
0.3461 20 150 0.3492
0.3222 20 160 0.3202
0.3043 20 170 0.2921
0.2727 20 180 0.2651
0.2378 20 190 0.2403
0.2229 20 200 0.2184
0.2121 20 210 0.1990
0.1891 20 220 0.1834
0.1867 20 230 0.1723
0.1848 20 240 0.1654
0.1732 20 250 0.1631

Framework versions

  • Transformers 4.45.1
  • Pytorch 2.5.0
  • peft 0.13.2
  • Datasets 3.0.1
  • Tokenizers 0.20.1