Spaces:
Running
Running
| title: LBW Guard Colab Tests | |
| emoji: 🧪 | |
| colorFrom: blue | |
| colorTo: green | |
| sdk: gradio | |
| python_version: "3.10" | |
| app_file: app.py | |
| suggested_hardware: cpu-basic | |
| models: | |
| - Qwen/Qwen2.5-0.5B | |
| datasets: | |
| - Salesforce/wikitext | |
| tags: | |
| - optimizer | |
| - training | |
| - colab | |
| - gradio | |
| Copyright (c) Qluon Inc. All rights reserved. | |
| Provided for Learn-By-Wire Guard evaluation and customer testing under the applicable Qluon license terms. | |
| # LBW Guard Colab Tests | |
| This Space packages the LBW Guard customer Colab notebooks: | |
| - `LBW_Guard_Easy_Test_COLAB.ipynb`: fast AdamW vs `lbw_guard` smoke test. | |
| - `LBW_Guard_Ablation_Test_COLAB.ipynb`: ablation-style AdamW baseline and `lbw_guard` comparison. | |
| Use the app to download either notebook, then open it in Google Colab with a GPU runtime. | |
| The notebooks install `LBW-Guard` from Python package distribution and do not import local source folders. | |
| ## Related Paper | |
| **Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency** | |
| - Author: Anis Radianis | |
| - arXiv: https://arxiv.org/abs/2605.19008 | |
| - DOI: https://doi.org/10.48550/arXiv.2605.19008 | |
| If you use these notebooks or the `lbw-guard` package in evaluation, please cite the paper above. | |