🧭 CompassAI — Qwen2.5-3B GIS LoRA

Fine-tuned version of Qwen/Qwen2.5-3B-Instruct for GIS intent detection and ArcGIS JS API 4.x code generation.

Training Details

Method: QLoRA (4-bit quantization + LoRA rank 16)
Task: Natural language → GIS API call (JSON)
Languages: English + Arabic
Base model: Qwen/Qwen2.5-3B-Instruct

Supported Intents

select_by_attribute — SQL-based feature filtering
select_by_location — Spatial proximity queries
count_aggregate — Statistical summaries
zoom_navigate — Map navigation
layer_toggle — Layer visibility control
spatial_filter — Polygon-based selection

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained('Qwen/Qwen2.5-3B-Instruct')
model = PeftModel.from_pretrained(base_model, 'rafat234/compass-ai-qwen2.5-3b-gis-lora')
tokenizer = AutoTokenizer.from_pretrained('rafat234/compass-ai-qwen2.5-3b-gis-lora')

Downloads last month: 6

Inference Providers NEW

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

Model tree for rafat234/CompassAI-G1

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Adapter

(1277)

this model