Downloads · 30 days
0
Zhouyang626/Kronos-V4-8stocks-5min
Kronos-V4-8stocks-5min is a time series forecasting model from Zhouyang626. Use it for the time series forecasting task on the model card, and read the license before you ship it in a product. It is set up for kronos. The card lists the license as apache-2.0.
基于 NeoQuasar/Kronos-small 微调的 A 股多标的联合预测模型。
Downloads · 30 days
0
Access
Public
Updated Apr 3, 2026
Repo size
115 MB
Likes
1
Public
Click a slice to open those files.
.safetensors115 MB · 100%
From the Hugging Face model README
基于 NeoQuasar/Kronos-small 微调的 A 股多标的联合预测模型。
| 项目 | 详情 |
|---|---|
| 基座模型 | NeoQuasar/Kronos-small |
| 微调数据 | 8 只 A 股 × 6 年 5 分钟 K 线 |
| 总数据量 | 461,856 条 |
| 训练方式 | 分块接力续训 (4-Part Sequential Chunking) |
| 训练设备 | CPU (纯 CPU 训练) |
| 训练耗时 | ~60 小时 |
| 股票 | 代码 |
|---|---|
| 捷佳伟创 | sz.300724 |
| 帝尔激光 | sz.300776 |
| 迈为股份 | sz.300751 |
| 西藏城投 | sh.600773 |
| 富临精工 | sz.300432 |
| 德业股份 | sh.605117 |
| 艾罗能源 | sh.688717 |
| 拉普拉斯 | sh.688726 |
from kronos import Kronos, KronosTokenizer, KronosPredictor
tokenizer = KronosTokenizer.from_pretrained("Zhouyang626/Kronos-V4-8stocks-5min", subfolder="tokenizer/best_model")
model = Kronos.from_pretrained("Zhouyang626/Kronos-V4-8stocks-5min", subfolder="basemodel/best_model")
predictor = KronosPredictor(model, tokenizer, device="cpu", max_context=512)