Modelpublic

CodeStrux-Tech/tac-1-lora

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes5downloads

Model Card

tac-1-lora — QLoRA adapter for tac-1

Overview

This is the QLoRA adapter that produced `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`.

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`.