Text Generation
PEFT
Safetensors
Spanish
lora
qlora
sft
trl
unsloth
address-parsing
costa-rica
qwen3
conversational
Instructions to use CodeStrux-Tech/tac-1-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use CodeStrux-Tech/tac-1-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "CodeStrux-Tech/tac-1-lora") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
|
Download README.md from CodeStrux-Tech/tac-1-lora: direct link, hf CLI and curl.
- Browser
- Download file 1.94 kB
-
https://huggingface.co/CodeStrux-Tech/tac-1-lora/resolve/main/README.md
- Command line
-
hf download hf://CodeStrux-Tech/tac-1-lora/README.md
-
curl -L -o README.md https://huggingface.co/CodeStrux-Tech/tac-1-lora/resolve/main/README.md
1.94 kB
| 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. | |