/FinGPT

Data-Centric FinGPT. Open-source for open finance! Revolutionize 🔥 We release the trained model on HuggingFace.

Primary LanguageJupyter NotebookMIT LicenseMIT

Data-Centric FinGPT: Open-source for Open Finance.

Downloads Downloads Python 3.8 PyPI License

Let us DO NOT expect Wall Street to open-source LLMs nor open APIs, due to FinTech institutes' internal regulations and policies.

Blueprint of FinGPT

Disclaimer: We are sharing codes for academic purposes under the MIT education license. 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.

Why FinGPT?

1). Finance is highly dynamic. BloombergGPT trained an LLM using a mixture of finance data and general-purpose data, which took about 53 days, at a cost of around $3M). It is costly to retrain an LLM model like BloombergGPT every month or every week, thus lightweight adaptation is highly favorable. FinGPT can be fine-tuned swiftly to incorporate new data (the cost falls significantly, less than $300 per fine-tuning).

2). Democratizing Internet-scale financial data is critical, say allowing timely updates of the model (monthly or weekly updates) using an automatic data curation pipeline. BloombergGPT has privileged data access and APIs, while FinGPT presents a more accessible alternative. It prioritizes lightweight adaptation, leveraging the best available open-source LLMs.

3). The key technology is "RLHF (Reinforcement learning from human feedback)", which is missing in BloombergGPT. RLHF enables an LLM model to learn individual preferences (risk-aversion level, investing habits, personalized robo-advisor, etc.), which is the "secret" ingredient of ChatGPT and GPT4.

FinGPT Demos

  • FinGPT V3 (Updated on 10/12/2023)

    • What's new: Best trainable and inferable FinGPT for sentiment analysis on a single RTX 3090, which is even better than GPT-4 and ChatGPT Finetuning.

    • FinGPT v3 series are LLMs finetuned with the LoRA method on the News and Tweets sentiment analysis dataset which achieve the best scores on most of the financial sentiment analysis datasets with low cost.

    • FinGPT v3.3 use llama2-13b as base model; FinGPT v3.2 uses llama2-7b as base model; FinGPT v3.1 uses chatglm2-6B as base model.

    • Benchmark Results:

    • Weighted F1 FPB FiQA-SA TFNS NWGI Devices Time Cost
      FinGPT v3.3 0.882 0.874 0.903 0.643 1 × RTX 3090 17.25 hours $17.25
      FinGPT v3.2 0.850 0.860 0.894 0.636 1 × A100 5.5 hours $ 22.55
      FinGPT v3.1 0.855 0.850 0.875 0.642 1 × A100 5.5 hours $ 22.55
      FinGPT (8bit) 0.855 0.847 0.879 0.632 1 × RTX 3090 6.47 hours $ 6.47
      FinGPT (QLoRA) 0.777 0.752 0.828 0.583 1 × RTX 3090 4.15 hours $ 4.15
      OpenAI Fine-tune 0.878 0.887 0.883 - - - -
      GPT-4 0.833 0.630 0.808 - - - -
      FinBERT 0.880 0.596 0.733 0.538 4 × NVIDIA K80 GPU - -
      Llama2-7B 0.390 0.800 0.296 0.503 2048 × A100 21 days $ 4.23 million
      BloombergGPT 0.511 0.751 - - 512 × A100 53 days $ 2.67 million

      Cost per GPU hour. For A100 GPUs, the AWS p4d.24xlarge instance, equipped with 8 A100 GPUs is used as a benchmark to estimate the costs. Note that BloombergGPT also used p4d.24xlarge As of July 11, 2023, the hourly rate for this instance stands at $32.773. Consequently, the estimated cost per GPU hour comes to $32.77 divided by 8, resulting in approximately $4.10. With this value as the reference unit price (1 GPU hour). BloombergGPT estimated cost= 512 x 53 x 24 = 651,264 GPU hours x $4.10 = $2,670,182.40. For RTX 3090, we assume its cost per hour is approximately $1.0, which is actually much higher than available GPUs from platforms like vast.ai.

    • Reproduce the results by running benchmarks, and the detailed tutorial is on the way.

    • Finetune your own FinGPT v3 model with the LoRA method on only an RTX 3090 with this notebook in 8bit or this notebook in int4 (QLoRA)

  • FinGPT V1

    • FinGPT by finetuning ChatGLM2 / Llama2 with LoRA with the market-labeled data for the Chinese Market

Instruction Tuning Datasets

Datasets Train Rows Test Rows Description
fingpt-sentiment-train 76.8K N/A Sentiment Analysis Training Instructions
fingpt-finred 27.6k 5.11k Financial Relation Extraction Instrutions
fingpt-headline 82.2k 20.5k Financial Headline Analysis Instructions
fingpt-ner 511 98 Financial Named-Entity Recognition Instructions
fingpt-fiqa_qa 17.1k N/A Financial Q&A Instructions
fingpt-fineval 1.06k 265 Chinese Multiple-Choice Questions Instructions

Tutorials

[Training] Beginner’s Guide to FinGPT: Training with LoRA and ChatGLM2–6B One Notebook, $10 GPU

Understanding FinGPT: An Educational Blog Series

FinGPT Ecosystem

FinGPT embraces a full-stack framework for FinLLMs with five layers:

  1. Data source layer: This layer assures comprehensive market coverage, addressing the temporal sensitivity of financial data through real-time information capture.
  2. Data engineering layer: Primed for real-time NLP data processing, this layer tackles the inherent challenges of high temporal sensitivity and low signal-to-noise ratio in financial data.
  3. LLMs layer: Focusing on a range of fine-tuning methodologies such as LoRA, this layer mitigates the highly dynamic nature of financial data, ensuring the model’s relevance and accuracy.
  4. Task layer: This layer is responsible for executing fundamental tasks. These tasks serve as the benchmarks for performance evaluations and cross-comparisons in the realm of FinLLMs
  5. Application layer: Showcasing practical applications and demos, this layer highlights the potential capability of FinGPT in the financial sector.
  • FinGPT Framework: Open-Source Financial Large Language Models
  • FinGPT-RAG: We present a retrieval-augmented large language model framework specifically designed for financial sentiment analysis, optimizing information depth and context through external knowledge retrieval, thereby ensuring nuanced predictions.
  • FinGPT-FinNLP: FinNLP provides a playground for all people interested in LLMs and NLP in Finance. Here we provide full pipelines for LLM training and finetuning in the field of finance. The full architecture is shown in the following picture. Detail codes and introductions can be found here. Or you may refer to the wiki
  • FinGPT-Benchmark: We introduce a novel Instruction Tuning paradigm optimized for open-source Large Language Models (LLMs) in finance, enhancing their adaptability to diverse financial datasets while also facilitating cost-effective, systematic benchmarking from task-specific, multi-task, and zero-shot instruction tuning tasks.

Open-Source Base Model used in the LLMs layer of FinGPT

  • Feel free to contribute more open-source base models tailored for various language-specific financial markets.
Base Model Pretraining Tokens Context Length Model Advantages Model Size Experiment Results Applications
Llama-2 2 Trillion 4096 Llama-2 excels on English-based market data llama-2-7b and Llama-2-13b llama-2 consistently shows superior fine-tuning results Financial Sentiment Analysis, Robo-Advisor
Falcon 1,500B 2048 Maintains high-quality results while being more resource-efficient falcon-7b Good for English market data Financial Sentiment Analysis
MPT 1T 2048 MPT models can be trained with high throughput efficiency and stable convergence mpt-7b Good for English market data Financial Sentiment Analysis
Bloom 366B 2048 World’s largest open multilingual language model bloom-7b1 Good for English market data Financial Sentiment Analysis
ChatGLM2 1.4T 32K Exceptional capability for Chinese language expression chatglm2-6b Shows prowess for Chinese market data Financial Sentiment Analysis, Financial Report Summary
Qwen 2.2T 8k Fast response and high accuracy qwen-7b Effective for Chinese market data Financial Sentiment Analysis
InternLM 1.8T 8k Can flexibly and independently construct workflows internlm-7b Effective for Chinese market data Financial Sentiment Analysis
  • Benchmark Results for the above open-source Base Models in the financial sentiment analysis task using the same instruction template for SFT (LoRA):
    Weighted F1/Acc Llama2 Falcon MPT Bloom ChatGLM2 Qwen InternLM
    FPB 0.863/0.863 0.846/0.849 0.872/0.872 0.810/0.810 0.850/0.849 0.854/0.854 0.709/0.714
    FiQA-SA 0.871/0.855 0.840/0.811 0.863/0.844 0.771/0.753 0.864/0.862 0.867/0.851 0.679/0.687
    TFNS 0.896/0.895 0.893/0.893 0.907/0.907 0.840/0.840 0.859/0.858 0.883/0.882 0.729/0.731
    NWGI 0.649/0.651 0.636/0.638 0.640/0.641 0.573/0.574 0.619/0.629 0.638/0.643 0.498/0.503

News

ChatGPT at AI4Finance

Introductory

The Journey of Open AI GPT models. GPT models explained. Open AI's GPT-1, GPT-2, GPT-3.

(Financial) Big Data

Interesting Demos

  • GPT-3 Creative Fiction Creative writing by OpenAI’s GPT-3 model, demonstrating poetry, dialogue, puns, literary parodies, and storytelling. Plus advice on effective GPT-3 prompt programming & avoiding common errors.

ChatGPT for FinTech

ChatGPT Trading Bot

Citing FinGPT

@article{yang2023fingpt,
  title={FinGPT: Open-Source Financial Large Language Models},
  author={Yang, Hongyang and Liu, Xiao-Yang and Wang, Christina Dan},
  journal={FinLLM Symposium at IJCAI 2023},
  year={2023}
}
@article{zhang2023instructfingpt,
      title={Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models}, 
      author={Boyu Zhang and Hongyang Yang and Xiao-Yang Liu},
      journal={FinLLM Symposium at IJCAI 2023},
      year={2023}
}
@article{zhang2023fingptrag,
  title={Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models},
  author={Zhang, Boyu and Yang, Hongyang and Zhou, tianyu and Babar, Ali and Liu, Xiao-Yang},
 journal = {ACM International Conference on AI in Finance (ICAIF)},
  year={2023}
}

Links