Instructions to use gxcsoccer/kronos-mlx-tokenizer-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use gxcsoccer/kronos-mlx-tokenizer-base with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir kronos-mlx-tokenizer-base gxcsoccer/kronos-mlx-tokenizer-base
- KRONOS
How to use gxcsoccer/kronos-mlx-tokenizer-base 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
- Local Apps Settings
- LM Studio
metadata
license: mit
library_name: kronos-mlx
pipeline_tag: time-series-forecasting
tags:
- mlx
- apple-silicon
- finance
- kronos
- tokenizer
base_model: NeoQuasar/Kronos-Tokenizer-base
Kronos-Tokenizer-base (MLX)
Apple MLX port of NeoQuasar/Kronos-Tokenizer-base — the BSQ (Binary Spherical Quantizer) tokenizer that compresses OHLCV candlestick sequences into hierarchical discrete tokens for the Kronos family of forecasting models.
Use it together with one of the MLX-native Kronos predictors, e.g. gxcsoccer/kronos-mlx-small.
Usage
from kronos_mlx import Kronos, KronosTokenizer, KronosPredictor
tokenizer = KronosTokenizer.from_pretrained("gxcsoccer/kronos-mlx-tokenizer-base")
model = Kronos.from_pretrained("gxcsoccer/kronos-mlx-small")
predictor = KronosPredictor(model, tokenizer, max_context=512)
Original
- Upstream: shiyu-coder/Kronos
- PyTorch weights: NeoQuasar/Kronos-Tokenizer-base