umuthopeyildirim
commited on
Commit
•
500efce
1
Parent(s):
621f507
Update README.md
Browse files
README.md
CHANGED
@@ -7,4 +7,30 @@ language:
|
|
7 |
library_name: transformers
|
8 |
tags:
|
9 |
- finance
|
10 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
library_name: transformers
|
8 |
tags:
|
9 |
- finance
|
10 |
+
---
|
11 |
+
|
12 |
+
# Fin-RWKV: Attention Free Financal Expert (WIP)
|
13 |
+
Fin-RWKV is a cutting-edge, attention-free model designed specifically for financial analysis and prediction. Developed as part of a MindsDB Hackathon, this model leverages the simplicity and efficiency of the RWKV architecture to process financial data, providing insights and forecasts with remarkable accuracy. Fin-RWKV is tailored for professionals and enthusiasts in the finance sector who seek to integrate advanced deep learning techniques into their financial analyses.
|
14 |
+
|
15 |
+
## Features
|
16 |
+
- Attention-Free Architecture: Utilizes the RWKV (Recurrent Weighted Kernel-based) model, which bypasses the complexity of attention mechanisms while maintaining high performance.
|
17 |
+
- Lower Costs: 10x to over a 100x+ lower inference cost, 2x to 10x lower training cost
|
18 |
+
- Tinyyyy: Lightweight enough to run on CPUs in real-time bypassing the GPU - and is able to run on your laptop today
|
19 |
+
- Finance-Specific Training: Trained on the gbharti/finance-alpaca dataset, ensuring that the model is finely tuned for financial data analysis.
|
20 |
+
- Transformers Library Integration: Built on the popular 'transformers' library, ensuring easy integration with existing ML pipelines and applications.
|
21 |
+
|
22 |
+
## Competing Against
|
23 |
+
- [BloombergGPT](https://www.bloomberg.com/company/press/bloomberggpt-50-billion-parameter-llm-tuned-finance/)
|
24 |
+
- [FinGPT](https://huggingface.co/FinGPT)
|
25 |
+
|
26 |
+
| Architecture | Status | Compute Efficiency | Largest Model | Trained Token | Link |
|
27 |
+
|--------------|--------|--------------------|---------------|---------------|------|
|
28 |
+
| (Fin)RWKV | In Production | O ( N ) | 14B | 500B++ (the pile+) | [Paper](https://arxiv.org/abs/2305.13048) |
|
29 |
+
| Ret Net (Microsoft) | Research | O ( N ) | 6.7B | 100B (mixed) | [Paper](https://arxiv.org/abs/2307.08621) |
|
30 |
+
| State Space (Stanford) | Prototype | O ( Log N ) | 355M | 15B (the pile, subset) | [Paper](https://arxiv.org/abs/2302.10866) |
|
31 |
+
| Liquid (MIT) | Research | - | <1M | - | [Paper](https://arxiv.org/abs/2302.10866) |
|
32 |
+
| Transformer Architecture (included for contrasting reference) | In Production | O ( N^2 ) | 800B (est) | 13T++ (est) | - |
|
33 |
+
|
34 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/631ea4247beada30465fa606/7vAOYsXH1vhTyh22o6jYB.png" width="500" alt="Inference computational cost vs. Number of tokens">
|
35 |
+
|
36 |
+
_Note: Needs more data and training, testing purposes only._
|