Text Generation
Transformers
PyTorch
Safetensors
English
rwkv
finance
Inference Endpoints
fin-rwkv-169M / README.md
umuthopeyildirim's picture
Update README.md
859dba4 verified
metadata
license: apache-2.0
datasets:
  - gbharti/finance-alpaca
language:
  - en
library_name: transformers
tags:
  - finance
widget:
  - text: >-
      Is this headline positive or negative? Headline: Australian Tycoon Forrest
      Shuts Nickel Mines After Prices Crash.
    example_title: Sentiment analysis
  - text: >-
      Aluminum price per KG is 50$. Forecast max: +1$ min:+0.3$. What should be
      the current price of aluminum?
    example_title: Forecast

Fin-RWKV: Attention Free Financal Expert (WIP)

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.

Use Cases

  • Sentiment analysis
  • Forecast
  • Product Pricing

Features

  • Attention-Free Architecture: Utilizes the RWKV (Recurrent Weighted Kernel-based) model, which bypasses the complexity of attention mechanisms while maintaining high performance.
  • Lower Costs: 10x to over a 100x+ lower inference cost, 2x to 10x lower training cost
  • Tinyyyy: Lightweight enough to run on CPUs in real-time bypassing the GPU - and is able to run on your laptop today
  • Finance-Specific Training: Trained on the gbharti/finance-alpaca dataset, ensuring that the model is finely tuned for financial data analysis.
  • Transformers Library Integration: Built on the popular 'transformers' library, ensuring easy integration with existing ML pipelines and applications.

Competing Against

Name Param Count Cost Inference Cost
Fin-RWKV 169M $1.45 Free on HuggingFace 🤗 & Low-End CPU
BloombergGPT 50 Billion $1.3 million Enterprise GPUs
FinGPT 7 Bilion $302.4 Consumer GPUs
Architecture Status Compute Efficiency Largest Model Trained Token Link
(Fin)RWKV In Production O ( N ) 14B 500B++ (the pile+) Paper
Ret Net (Microsoft) Research O ( N ) 6.7B 100B (mixed) Paper
State Space (Stanford) Prototype O ( Log N ) 355M 15B (the pile, subset) Paper
Liquid (MIT) Research - <1M - Paper
Transformer Architecture (included for contrasting reference) In Production O ( N^2 ) 800B (est) 13T++ (est) -
Inference computational cost vs. Number of tokens

Note: Needs more data and training, testing purposes only.