Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,19 @@
|
|
1 |
---
|
2 |
base_model: EleutherAI/gpt-neo-125M
|
3 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
---
|
@@ -8,17 +21,26 @@ base_model: EleutherAI/gpt-neo-125M
|
|
8 |
library_name: peft
|
9 |
---
|
10 |
|
11 |
-
# Model
|
12 |
-
IndicFinGPT’s design enables chartless trading by providing real-time, data-driven insights without relying on traditional graphical representations. By understanding key financial indicators—such as moving averages, momentum shifts, and volume trends—it interprets and communicates these patterns through concise, actionable outputs. This makes it ideal for traders who seek swift, high-quality information without needing to analyze charts.
|
13 |
-
The main purpose behind developing IndicFinGPT is to empower Indian market participants with a tool finely tuned to the country's financial environment. It bridges the gap between complex market data and clear, efficient decision-making, especially valuable for professionals who may not have the time or resources to analyze visual data in real-time. This model enables a streamlined trading experience by filtering noise and focusing on essential information specific to India's trading dynamics.
|
14 |
|
15 |
-
|
|
|
|
|
|
|
|
|
16 |
|
17 |
-
IndicFinGPT is a Small Language Model (SML) that uses bsed architecture of GPT--NEO125M, and has been retrained on its top-layers for the benefit of Indian investors who want to do chartless trading. Although, it provides chartless insights, yet it uses technical indicators to arrive at conclusions and predictions. It represents a significant advancement in utilizing cutting-edge AI technology to understand and analyze Bharatiya financial ecosystems, bridging the gap between global AI innovations and India's unique trading dynamics.
|
18 |
<p align="center">
|
19 |
<img src="https://huggingface.co/bhaskartripathi/GPT_Neo_Market_Analysis/resolve/main/indicBull.JPG" alt="IndicFinGPT Logo" width="400" height="300">
|
|
|
20 |
</p>
|
21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
## Key Highlights
|
23 |
|
24 |
IndicFinGPT
|
@@ -236,4 +258,4 @@ IndicFinGPT democratizes sophisticated AI-based financial analysis for the India
|
|
236 |
## Contact
|
237 |
- **Email**: [email protected]
|
238 |
- **HuggingFace**: [@bhaskartripathi](https://huggingface.co/bhaskartripathi)
|
239 |
-
- **Google Scholar**: [Profile](https://scholar.google.com/citations?user=SCHOLAR_ID)
|
|
|
1 |
---
|
2 |
base_model: EleutherAI/gpt-neo-125M
|
3 |
library_name: peft
|
4 |
+
license: mit
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- Pattern Detection Rate
|
11 |
+
- Cross-Entropy Loss
|
12 |
+
tags:
|
13 |
+
- finance, IndianStocks, Technical Analysis, Chartless Trading
|
14 |
+
language:
|
15 |
+
- en
|
16 |
+
pipeline_tag: question-answering
|
17 |
---
|
18 |
|
19 |
---
|
|
|
21 |
library_name: peft
|
22 |
---
|
23 |
|
24 |
+
# Model Description
|
|
|
|
|
25 |
|
26 |
+
**IndicFinGPT** is a specialized transformer model, re-engineered from **EleutherAI's GPT-Neo-125M** architecture, which is a GPT-3 class architecture, designed specifically for the **Indian financial market**. The model has undergone **retraining on its top layers** to enhance its performance in providing insights into the **top 100 companies listed in the NIFTY50 Index, BSE, and NSE exchanges**.
|
27 |
+
The primary objective of this model is to **serve the unique needs of Indian stock markets** and **investors engaged in chartless trading**. IndicFinGPT aims to provide insights that could **minimize capital loss and drawdowns** while **maximizing financial ratios** such as the **Sharpe, Sortino, Calmar, Omega, and Treynor Ratios**. Additionally, the model is designed to help in **reducing maximum drawdowns** in financial portfolios, offering a robust AI solution tailored to **India’s dynamic financial landscape**.
|
28 |
+
|
29 |
+
|
30 |
+
## First Indic-Stock Small Language Model Focused Top 100 Companies Listed in NSE and BSE Stock Exchanges
|
31 |
|
|
|
32 |
<p align="center">
|
33 |
<img src="https://huggingface.co/bhaskartripathi/GPT_Neo_Market_Analysis/resolve/main/indicBull.JPG" alt="IndicFinGPT Logo" width="400" height="300">
|
34 |
+
<strong>भारत का पहला AI मॉडल: शीर्ष 100 कंपनियों पर केंद्रित</strong>
|
35 |
</p>
|
36 |
|
37 |
+
|
38 |
+
## Training Data
|
39 |
+
|
40 |
+
**IndicFinGPT 125M** utilizes the **Pile dataset** created by EleutherAI and includes the **top 100 tickers** (by volume and liquidity) from Indian stock markets, covering data from **January 1, 2018, to October 30, 2024**. This dataset encompasses diverse market periods, including **pre-COVID-19 (stable), COVID-19 (volatile), and post-COVID-19 (recovery phase)**. Such comprehensive data exposure allows the model to recognize **problem-solution patterns across various bull and bear runs**.
|
41 |
+
The training data also incorporates **local influences** such as cultural factors and **market-specific volatility**, enhancing its ability to perform **automated technical analysis** for chartless trading. Key capabilities include identifying **classical chart patterns** using technical analysis, conducting **earnings analysis**, interpreting **market sentiment** from multiple sources, and **assessing risks**, all aimed at **improving decision-making for Indian investors**.
|
42 |
+
|
43 |
+
|
44 |
## Key Highlights
|
45 |
|
46 |
IndicFinGPT
|
|
|
258 |
## Contact
|
259 |
- **Email**: [email protected]
|
260 |
- **HuggingFace**: [@bhaskartripathi](https://huggingface.co/bhaskartripathi)
|
261 |
+
- **Google Scholar**: [Profile](https://scholar.google.com/citations?user=SCHOLAR_ID)
|