StackMap
Subscribe
Explore / Kronos
shiyu-coder

Kronos

The first open foundation model for financial candlesticks: trained on K-lines from 45 global exchanges, AAAI 2026, weights on Hugging Face with fine-tuning scripts for your own tasks.

34,439 5,788 Python MITupdated 3 months ago
finance
View on GitHubDispute this mapping →
Curator's take

A genuine first: a decoder-style foundation model that treats OHLCV candlesticks as a language, pre-trained across 45 exchanges — with the academic receipts (AAAI 2026) and the practical surface (HF weights, fine-tuning scripts, live demo) that most finance-ML repos lack. If you're building trading agents, this is the open forecasting prior to fine-tune on your instruments. NOT a trading strategy: it forecasts distributions over price structure, and the gap between a good forecast and a profitable, transaction-cost-surviving strategy is where quant careers go to die. Backtest honestly, mind regime shift, and remember every published financial model decays once the market meets it.

Mapped by ShipWithAI editors · links verified
README.md

Kronos: A Foundation Model for the Language of Financial Markets

Kronos is the first open-source foundation model for financial candlesticks (K-lines), trained on data from over 45 global exchanges.

📰 News

  • 🚩 [2025.11.10] Kronos has been accpeted by AAAI 2026.
  • 🚩 [2025.08.17] We have released the scripts for fine-tuning! Check them out to adapt Kronos to your own tasks.
  • 🚩 [2025.08.02] Our paper is now available on arXiv!

📜 Introduction

Kronos is a family of decoder-only foundation models, pre-trained specifically for the "language" of financial markets—K-line sequences. Unlike general-purpose TSFMs, Kronos is designed to handle the unique, high-noise characteristics of financial data. It leverages a novel two-stage framework:

  1. A specialized tokenizer first quantizes continuous, multi-dimensional K-line data (OHLCV) into hierarchical discrete tokens.
  2. A large, autoregressive Transformer is then pre-trained on these tokens, enabling it to serve as a unified model for diverse quantitative tasks.

✨ Live Demo

We have set up a live demo to visualize Kronos's forecasting results. The webpage showcases a forecast for the BTC/USDT trading pair over the next 24 hours.

👉 Access the Live Demo Here

📦 Model Zoo

We release a family of pre-trained models with varying capacities to suit different computational and application needs. All models are readily accessible from the Hugging Face Hub.

Model Tokenizer Context length Params Open-source
Kronos-mini Kronos-Tokenizer-2k 2048

Continue your stack

What teams reach for next — and why each earns a place beside Kronos. Ranked by curator confidence.