|
Download README.md from hundredl/StockClipData: direct link, hf CLI and curl.
- Browser
- Download file 2.85 kB
-
https://huggingface.co/hundredl/StockClipData/resolve/main/README.md
- Command line
-
hf download hf://hundredl/StockClipData/README.md
-
curl -L -H "Authorization: Bearer $HF_TOKEN" -o README.md https://huggingface.co/hundredl/StockClipData/resolve/main/README.md
2.85 kB
| # Project: Hundred1 | |
| This repository contains the directory structure and data files for the Hundred1 project. Below is a detailed explanation of each folder and its contents. | |
| ## Directory Structure | |
| ``` | |
| hundred1 | |
| βββ ckpt # model parameters trained by data | |
| βββ data # Chinese stock market data | |
| βββ model # model code and some running and testing results | |
| βββ data2 # US stock market data | |
| β βββ text | |
| β βββ stock | |
| βββ .gitattributes # initial commit | |
| ``` | |
| ## Folder Explanations | |
| ### ckpt | |
| This folder contains the model parameters that were trained using the data. These parameters are crucial for replicating the model results and for further training or fine-tuning. | |
| ### data | |
| This folder includes Chinese stock market data. The data is essential for training and testing models focused on the Chinese stock market. | |
| ### model | |
| The `model` folder contains the model code along with some running and testing results. This includes the scripts necessary to build, train, and evaluate the models, as well as any output results from test runs. | |
| ### data2 | |
| The `data2` folder is designated for US stock market data. It contains two subdirectories: | |
| - **text**: This subdirectory includes text data related to US stocks. | |
| - **stock**: This subdirectory includes stock data with corresponding time ranges. | |
| Both the text data and stock data in the `data2` folder have corresponding time ranges. You can first check the available time ranges and then select and download the data in bulk as needed. | |
| ## Instructions for Use | |
| 1. **Explore Data Ranges**: Before downloading data in bulk, it is recommended to first explore the available time ranges. This will help you select the specific data sets that are relevant to your analysis or model training. | |
| 2. **Download Data**: After identifying the required time ranges, you can proceed to download the data in bulk. Ensure that you have enough storage space and that your internet connection is stable during the download process. | |
| 3. **Model Training and Evaluation**: Use the data in the `data` and `data2` folders to train and evaluate your models. The model parameters in the `ckpt` folder can be used to replicate the results or to continue training from a previous state. | |
| 4. **Code and Results**: Refer to the `model` folder for all the necessary code and scripts to run the models. The folder also contains results from initial test runs, which can be useful for benchmarking and comparison. | |
| ## Contribution | |
| If you wish to contribute to this project, please fork the repository, create a new branch, and submit a pull request with your changes. Ensure that your contributions are well-documented and tested. | |
| ## License | |
| This project is licensed under the MIT License. See the `LICENSE` file for more details. | |