Instructions to use talant28/Kronos-TW-Tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KRONOS
How to use talant28/Kronos-TW-Tokenizer with KRONOS:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
| language: zh | |
| license: mit | |
| tags: | |
| - finance | |
| - time-series | |
| - taiwan | |
| - stock | |
| - kronos | |
| base_model: NeoQuasar/Kronos-Tokenizer-base | |
| # Kronos-TW-Tokenizer | |
| Kronos VQ Tokenizer fine-tuned on Taiwan Stock Exchange (TWSE) daily OHLCV data. | |
| ## Base Model | |
| [NeoQuasar/Kronos-Tokenizer-base](https://huggingface.co/NeoQuasar/Kronos-Tokenizer-base) | |
| ## Training Data | |
| - Source: TWSE listed stocks (613 stocks after quality filtering) | |
| - Period: 2010-01-01 ~ 2024-12-31 | |
| - Features: open, high, low, close, volume, amount | |
| - Lookback: 90 trading days | |
| ## Training Config | |
| - Epochs: 3 | |
| - Batch size: 8 (effective 256 with gradient accumulation) | |
| - Learning rate: 2e-4 | |
| - Hardware: RTX 4080 Laptop 12GB | |