# How to Fine-Tune the Kronos Tokenizer for New Market Data: A Complete Guide

> Learn to fine-tune the Kronos tokenizer for new market data. This guide details preparing CSV data, configuring YAML, and running the finetune script to adapt the Binary Spherical Quantizer.

- Repository: [ShiYu/Kronos](https://github.com/shiyu-coder/Kronos)
- Tags: how-to-guide
- Published: 2026-04-10

---

**Fine-tune the Kronos tokenizer by preparing a CSV with six market features, configuring a YAML file with your data path and training epochs, and running [`finetune_csv/finetune_tokenizer.py`](https://github.com/shiyu-coder/Kronos/blob/main/finetune_csv/finetune_tokenizer.py) to adapt the Binary Spherical Quantizer to your specific market distribution.**

Adapting the Kronos tokenizer to new market data allows the model to learn domain-specific quantization patterns that improve downstream prediction accuracy. This process involves self-supervised fine-tuning of the **Binary Spherical Quantizer (BSQuantizer)** on your custom