GStars
    AI4Finance-Foundation

    AI4Finance-Foundation/FinGPT

    FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

    ai
    llm
    machine-learning
    nlp
    chatgpt
    finance
    fingpt
    fintech
    large-language-models
    prompt-engineering
    pytorch
    reinforcement-learning
    robo-advisor
    sentiment-analysis
    technical-analysis
    Jupyter Notebook
    MIT
    17.4K stars
    2.5K forks
    17.4K watching
    Updated 2/27/2026
    View on GitHub
    Backblaze Advertisement

    Loading star history...

    Health Score

    5.6

    Weekly Growth

    +0

    +0.0% this week

    Contributors

    1

    Total contributors

    Open Issues

    79

    Generated Insights

    About FinGPT

    image

    FinGPT: Open-Source Financial Large Language Models

    Downloads Downloads Python 3.8 PyPI License

    Let us not expect Wall Street to open-source LLMs or open APIs, due to FinTech institutes' internal regulations and policies.

    Blueprint of FinGPT

    https://huggingface.co/FinGPT

    Visitors

    What's New:

    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.

    Milestone of AI Robo-Advisor: FinGPT-Forecaster

    Try the latest released FinGPT-Forecaster demo at our HuggingFace Space

    The dataset for FinGPT-Forecaster: https://huggingface.co/datasets/FinGPT/fingpt-forecaster-dow30-202305-202405

    demo_interface

    Enter the following inputs:

    1. ticker symbol (e.g. AAPL, MSFT, NVDA)
    2. the day from which you want the prediction to happen (yyyy-mm-dd)
    3. the number of past weeks where market news are retrieved
    4. whether to add the latest basic financials as additional information

    Click Submit！ And you'll be responded with a well-rounded analysis of the company and a prediction for next week's stock price movement!

    For detailed and more customized implementation, please refer to FinGPT-Forecaster

    FinGPT Demos:

    Current State-of-the-arts for Financial Sentiment Analysis

    • 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 F1FPBFiQA-SATFNSNWGIDevicesTimeCost
        FinGPT v3.30.8820.8740.9030.6431 × RTX 309017.25 hours$17.25
        FinGPT v3.20.8500.8600.8940.6361 × A1005.5 hours$ 22.55
        FinGPT v3.10.8550.8500.8750.6421 × A1005.5 hours$ 22.55
        FinGPT (8bit)0.8550.8470.8790.6321 × RTX 30906.47 hours$ 6.47
        FinGPT (QLoRA)0.7770.7520.8280.5831 × RTX 30904.15 hours$ 4.15
        OpenAI Fine-tune0.8780.8870.883----
        GPT-40.8330.6300.808----
        FinBERT0.8800.5960.7330.5384 × NVIDIA K80 GPU--
        Llama2-7B0.3900.8000.2960.5032048 × A10021 days$ 4.23 million
        BloombergGPT0.5110.751--512 × A10053 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 and Models

    The datasets we used, and the multi-task financial LLM models are available at https://huggingface.co/FinGPT

    Our Code

    DatasetsTrain RowsTest RowsDescription
    fingpt-sentiment-train76.8KN/ASentiment Analysis Training Instructions
    fingpt-finred27.6k5.11kFinancial Relation Extraction Instructions
    fingpt-headline82.2k20.5kFinancial Headline Analysis Instructions
    fingpt-ner51198Financial Named-Entity Recognition Instructions
    fingpt-fiqa_qa17.1kN/AFinancial Q&A Instructions
    fingpt-fineval1.06k265Chinese Multiple-Choice Questions Instructions

    Multi-task financial LLMs Models:

      demo_tasks = [
      'Financial Sentiment Analysis',
      'Financial Relation Extraction',
      'Financial Headline Classification',
      'Financial Named Entity Recognition',]
  demo_inputs = [
      "Glaxo's ViiV Healthcare Signs China Manufacturing Deal With Desano",
      "Apple Inc. Chief Executive Steve Jobs sought to soothe investor concerns about his health on Monday, saying his weight loss was caused by a hormone imbalance that is relatively simple to treat.",
      'gold trades in red in early trade; eyes near-term range at rs 28,300-28,600',
      'This LOAN AND SECURITY AGREEMENT dated January 27 , 1999 , between SILICON VALLEY BANK (" Bank "), a California - chartered bank with its principal place of business at 3003 Tasman Drive , Santa Clara , California 95054 with a loan production office located at 40 William St ., Ste .',]
  demo_instructions = [
      'What is the sentiment of this news? Please choose an answer from {negative/neutral/positive}.',
      'Given phrases that describe the relationship between two words/phrases as options, extract the word/phrase pair and the corresponding lexical relationship between them from the input text. The output format should be "relation1: word1, word2; relation2: word3, word4". Options: product/material produced, manufacturer, distributed by, industry, position held, original broadcaster, owned by, founded by, distribution format, headquarters location, stock exchange, currency, parent organization, chief executive officer, director/manager, owner of, operator, member of, employer, chairperson, platform, subsidiary, legal form, publisher, developer, brand, business division, location of formation, creator.',
      'Does the news headline talk about price going up? Please choose an answer from {Yes/No}.',
      'Please extract entities and their types from the input sentence, entity types should be chosen from {person/organization/location}.',]
    ModelsDescriptionFunction
    fingpt-mt_llama2-7b_loraFine-tuned Llama2-7b model with LoRAMulti-Task
    fingpt-mt_falcon-7b_loraFine-tuned falcon-7b model with LoRAMulti-Task
    fingpt-mt_bloom-7b1_loraFine-tuned bloom-7b1 model with LoRAMulti-Task
    fingpt-mt_mpt-7b_loraFine-tuned mpt-7b model with LoRAMulti-Task
    fingpt-mt_chatglm2-6b_loraFine-tuned chatglm-6b model with LoRAMulti-Task
    fingpt-mt_qwen-7b_loraFine-tuned qwen-7b model with LoRAMulti-Task
    fingpt-sentiment_llama2-13b_loraFine-tuned llama2-13b model with LoRASingle-Task
    fingpt-forecaster_dow30_llama2-7b_loraFine-tuned llama2-7b model with LoRASingle-Task

    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 ModelPretraining TokensContext LengthModel AdvantagesModel SizeExperiment ResultsApplications
    Llama-22 Trillion4096Llama-2 excels on English-based market datallama-2-7b and Llama-2-13bllama-2 consistently shows superior fine-tuning resultsFinancial Sentiment Analysis, Robo-Advisor
    Falcon1,500B2048Maintains high-quality results while being more resource-efficientfalcon-7bGood for English market dataFinancial Sentiment Analysis
    MPT1T2048MPT models can be trained with high throughput efficiency and stable convergencempt-7bGood for English market dataFinancial Sentiment Analysis
    Bloom366B2048World’s largest open multilingual language modelbloom-7b1Good for English market dataFinancial Sentiment Analysis
    ChatGLM21.4T32KExceptional capability for Chinese language expressionchatglm2-6bShows prowess for Chinese market dataFinancial Sentiment Analysis, Financial Report Summary
    Qwen2.2T8kFast response and high accuracyqwen-7bEffective for Chinese market dataFinancial Sentiment Analysis
    InternLM1.8T8kCan flexibly and independently construct workflowsinternlm-7bEffective for Chinese market dataFinancial 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/AccLlama2FalconMPTBloomChatGLM2QwenInternLM
      FPB0.863/0.8630.846/0.8490.872/0.8720.810/0.8100.850/0.8490.854/0.8540.709/0.714
      FiQA-SA0.871/0.8550.840/0.8110.863/0.8440.771/0.7530.864/0.8620.867/0.8510.679/0.687
      TFNS0.896/0.8950.893/0.8930.907/0.9070.840/0.8400.859/0.8580.883/0.8820.729/0.731
      NWGI0.649/0.6510.636/0.6380.640/0.6410.573/0.5740.619/0.6290.638/0.6430.498/0.503

    All Thanks To Our Contributors :

    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}
}

@article{wang2023fingptbenchmark,
  title={FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets},
  author={Wang, Neng and Yang, Hongyang and Wang, Christina Dan},
  journal={NeurIPS Workshop on Instruction Tuning and Instruction Following},
  year={2023}
}
@article{2023finnlp,
  title={Data-centric FinGPT: Democratizing Internet-scale Data for Financial Large Language Models},
  author={Liu, Xiao-Yang and Wang, Guoxuan and Yang, Hongyang and Zha, Daochen},
  journal={NeurIPS Workshop on Instruction Tuning and Instruction Following},
  year={2023}
}

    LICENSE

    MIT License

    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.

    Discover Repositories

    Search across tracked repositories by name or description