---
license: apache-2.0
language:
  - es
library_name: peft
base_model: unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit
pipeline_tag: text-generation
tags:
  - lora
  - qlora
  - sft
  - trl
  - unsloth
  - address-parsing
  - costa-rica
  - qwen3
---

# tac-1-lora — QLoRA adapter for tac-1

## Overview

This is the QLoRA adapter that produced [`CodeStrux-Tech/tac-1`](https://huggingface.co/CodeStrux-Tech/tac-1). **Most users want the merged tac-1 repo**, not these adapter weights. Use this repo only if you need to inspect or extend the adapter directly.

## Loading with PEFT

PEFT loading requires the base model `unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit`.

## Training configuration

- **Base model:** Qwen/Qwen3-4B-Instruct-2507
- **Method:** QLoRA (r=16, α=32)
- **Learning rate:** 2e-4
- **Epochs:** 2
- **Max sequence length:** 4096
- **Steps:** 692
- **Final train loss:** 0.043
- **Hardware:** ~2 h 50 m on an RTX 4080 16 GB
- **Stack:** unsloth 2025.11.1 / transformers 4.57.2 / trl 0.23.0

## Training data

The adapter was trained on the tac-1 corpus: 5,532 examples (seed 0), 805 heldout (seed 1); `--max-legs 4`; 22 districts ingested, 19,042 POIs, 11 griddable; holdout districts grecia, curridabat, go-guadalupe excluded from training. See [`CodeStrux-Tech/tac-1-corpus`](https://huggingface.co/CodeStrux-Tech/tac-1-corpus).

### Training data attribution

Contains information from OpenStreetMap (https://www.openstreetmap.org/copyright), which is made available under the Open Database License (ODbL) 1.0. © OpenStreetMap contributors.

For full architecture, evaluation, and limitations, see [`CodeStrux-Tech/tac-1`](https://huggingface.co/CodeStrux-Tech/tac-1).

tac-1 is a derivative work of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507), Copyright 2024 Alibaba Cloud, licensed under the Apache License, Version 2.0. The upstream LICENSE is included in this repository.