| --- |
| license: apache-2.0 |
| base_model: Qwen/Qwen3.5-4B |
| pipeline_tag: text-generation |
| tags: |
| - code |
| - spatial |
| - sql |
| - GIS |
| - PostGIS |
| --- |
| |
| ### Model Information |
|
|
| This model, Qwen-3.5-4B-Instruct-Spatial-SQL-1.1, is an 4B, 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 ten geographic functions released in version 1.2. |
|
|
| **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: |
|
|
| ### Example Prompt / Prompt File |
|
|
| ### Examples |
|
|
| ### A Few Known Question Variation Examples |
|
|
| ### llama.cpp / Hyperparameter Recommendations For Inference |
|
|
| ### Agent Considerations |
|
|
| ### Further Reference - link this |
|
|
| ### Evaluation data |
|
|
| ### Training data |
| Custom synthetic |
|
|
| ### Training hyperparameters |
|
|
| ### Training results |
|
|
| | Training Loss | Step | Validation Loss | |
| |:-------------:|:----:|:---------------:| |
| | 1.1217 | 10 | 0.8837 | |
| | 0.8026 | 20 | 0.7469 | |
| | 0.7432 | 30 | 0.6925 | |
| | 0.6930 | 40 | 0.6455 | |
| | 0.6189 | 50 | 0.5935 | |
| | 0.5665 | 60 | 0.5342 | |
| | 0.4824 | 70 | 0.4802 | |
| | 0.4461 | 80 | 0.4557 | |
|
|
| ### Framework versions |
|
|
| - Transformers 4.46.1 |
| - Pytorch 2.5.1 |
| - peft 0.19.1 |
| - Datasets 5.0.0 |
| - Tokenizers 0.22.2 |
