ENGLISH ONLY - Use 8b models for alternate languages.
Model Information
This model, Llama-3.2-3B-Instruct-Spatial-SQL-1.1, 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 five primary geographic functions released in version 1.1.
Model developer: Mark Rodrigo
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 |
| Function | Question Input | Geo Input 1 | Geo Input 2 | SQL Execution Output |
|---|
| Distance | Distance question | Point, Line, or Polygon | Point, Line, or Polygon | Number - Distance between geometries 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;
DISTANCE
### INPUT: How far apart is the point and line? : 'Point(-109.87549823 38.60574249)' 'LineString(-109.24324628 38.76349931, -109.4821773 38.6875815)'
### Response: SELECT ST_Distance(gg1, gg2) As distance FROM (select 'Point(-109.87549823 38.60574249)' :: geography gg1, 'LineString(-109.24324628 38.76349931, -109.4821773 38.6875815)' :: geography gg2) 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?
DISTANCE
The distance between the polygon and the line is?
What is the distance between the points?
How far apart are the two lines?
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
Evaluation data
More information needed
Training data
Custom synthetic
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-4
- 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 | Step | Validation Loss |
|---|
| 0.8115 | 10 | 0.6781 |
| 0.6433 | 20 | 0.6173 |
| 0.6182 | 30 | 0.5445 |
| 0.4994 | 40 | 0.4888 |
| 0.4911 | 50 | 0.4265 |
| 0.4791 | 60 | 0.3477 |
| 0.3605 | 70 | 0.3096 |
| 0.3493 | 80 | 0.2850 |
| 0.3344 | 90 | 0.2604 |
| 0.1718 | 100 | 0.2508 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.5.1
- peft 0.13.2
- Datasets 3.1.0
- Tokenizers 0.21.0
