Spaces:
Runtime error
Runtime error
ReadME Init
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
title: FinGPT Forecaster Chinese
|
3 |
-
emoji:
|
4 |
colorFrom: pink
|
5 |
colorTo: gray
|
6 |
sdk: gradio
|
@@ -10,4 +10,16 @@ pinned: false
|
|
10 |
license: apache-2.0
|
11 |
---
|
12 |
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
title: FinGPT Forecaster Chinese
|
3 |
+
emoji: π
|
4 |
colorFrom: pink
|
5 |
colorTo: gray
|
6 |
sdk: gradio
|
|
|
10 |
license: apache-2.0
|
11 |
---
|
12 |
|
13 |
+
# This is the Chinese Version of FinGPT-Forecaster.
|
14 |
+
|
15 |
+
Targeted for the Chinese A-share market, we performed the instruction-based fine-tuning task on the market data of SZ50(δΈθ―50ζζ°) with LoRA and Llama-2-7B-chat base model.
|
16 |
+
|
17 |
+
Like our released FinGPT-Forecaster, this Chinese version is also able to take the **input of company's recent information**(News, Financial Basics, Stock Price) with the **output of future forecasting**(Positive&Negative Summary and Stock Price Trend Prediction).
|
18 |
+
|
19 |
+
Our training data was collected from public website such as (https://stock.eastmoney.com/) as well as the AKshare API(https://github.com/akfamily/akshare). Moreover, we also performed a solid data processing job to obtain high-quality instruction-tuning datasets.
|
20 |
+
|
21 |
+
For more detailed and customized implementation, refer to our **FinGPT project** <https://github.com/AI4Finance-Foundation/FinGPT>
|
22 |
+
|
23 |
+
**Disclaimer: Nothing herein is financial advice, and NOT a recommendation to trade real money. Please use common sense and always first consult a professional before trading or investing.**
|
24 |
+
|
25 |
+
|