test_dataset = load_from_disk('data/fingpt-forecaster-dow30v3-20221231-20230531-llama/')['test'] 数据是从哪里下载的

AI4Finance-Foundation / FinGPT

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

https://ai4finance.org

MIT License

12.75k stars 1.81k forks source link

test_dataset = load_from_disk('data/fingpt-forecaster-dow30v3-20221231-20230531-llama/')['test'] 数据是从哪里下载的 #137

Closed GL-Aronman closed 7 months ago

GL-Aronman commented 7 months ago

fingpt/FinGPT_Forecaster/demo.ipynb 里面的 test_dataset = load_from_disk('data/fingpt-forecaster-dow30v3-20221231-20230531-llama/')['test'] 请问这个数据是从哪里下载的

Noir97 commented 7 months ago

It's a test split from our generated dataset. But I'm sorry as we currently don't release it. You can try to reproduce a similar dataset with our provided data script prepare_data.ipynb. Feel free to reopen the issue if you have further questions.

hongxiong1230 commented 7 months ago

Hello! I am using the train.sh of the project of FinGPT_Forecaster, but the fine tuned model size is over 100G. The original stock data is about 70M. Do you know how to better obtain the fine tuned model?