FinGPT | Open Source Financial Large Language Models

[Mr.Brilliant 27]

This is the hidden content, please

• Sign In
• or
• Sign Up

FinGPT: Open-Source Financial Large Language Models

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

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

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

What's New:

• [Model Release] Nov, 2023: We release
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  !
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  ,
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  &
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  are available on Huggingface!
• [Paper Acceptance] Oct, 2023:
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  is accepted by
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  @ NeurIPS 2023
• [Paper Acceptance] Oct, 2023:
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  is accepted by
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  @ NeurIPS 2023
• [Model Release] Oct, 2023: We release the
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  produced when evaluating base-LLMs on
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [Paper Acceptance] Sep, 2023:
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  is accepted by
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [Model Release] Aug, 2023: We release the
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  
• [Paper Acceptance] Jul, 2023:
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  is accepted by
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  @IJCAI 2023
• [Paper Acceptance] Jul, 2023:
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  is accepted by
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  @IJCAI 2023
• [Medium Blog] Jun 2023:
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up

Why FinGPT?

1). Finance is highly dynamic.

This is the hidden content, please

• Sign In
• or
• Sign Up

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

This is the hidden content, please

• Sign In
• or
• Sign Up

The dataset for FinGPT-Forecaster:

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

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

This is the hidden content, please

• Sign In
• or
• Sign Up

FinGPT Demos:

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

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up

  • 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.

  • This is the hidden content, please

    • Sign In
    • or
    • Sign Up
    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
    This is the hidden content, please Sign In or Sign Up	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

    This is the hidden content, please

    • Sign In
    • or
    • Sign Up
    , 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

    This is the hidden content, please

    • Sign In
    • or
    • Sign Up
    in 8bit or this
    This is the hidden content, please

    • Sign In
    • or
    • Sign Up
    in int4 (QLoRA)

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  • 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

This is the hidden content, please

• Sign In
• or
• Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

Datasets	Train Rows	Test Rows	Description
This is the hidden content, please Sign In or Sign Up	76.8K	N/A	Sentiment Analysis Training Instructions
This is the hidden content, please Sign In or Sign Up	27.6k	5.11k	Financial Relation Extraction Instructions
This is the hidden content, please Sign In or Sign Up	82.2k	20.5k	Financial Headline Analysis Instructions
This is the hidden content, please Sign In or Sign Up	511	98	Financial Named-Entity Recognition Instructions
This is the hidden content, please Sign In or Sign Up	17.1k	N/A	Financial Q&A Instructions
This is the hidden content, please Sign In or Sign Up	1.06k	265	Chinese 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}.',]

Models	Description	Function
This is the hidden content, please Sign In or Sign Up	Fine-tuned Llama2-7b model with LoRA	Multi-Task
This is the hidden content, please Sign In or Sign Up	Fine-tuned falcon-7b model with LoRA	Multi-Task
This is the hidden content, please Sign In or Sign Up	Fine-tuned bloom-7b1 model with LoRA	Multi-Task
This is the hidden content, please Sign In or Sign Up	Fine-tuned mpt-7b model with LoRA	Multi-Task
This is the hidden content, please Sign In or Sign Up	Fine-tuned chatglm-6b model with LoRA	Multi-Task
This is the hidden content, please Sign In or Sign Up	Fine-tuned qwen-7b model with LoRA	Multi-Task
This is the hidden content, please Sign In or Sign Up	Fine-tuned llama2-13b model with LoRA	Single-Task
This is the hidden content, please Sign In or Sign Up	Fine-tuned llama2-7b model with LoRA	Single-Task

Tutorials

This is the hidden content, please

• Sign In
• or
• Sign Up

Understanding FinGPT: An Educational Blog Series

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• This is the hidden content, please

  • Sign In
  • or
  • Sign Up

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

This is the hidden content, please

• Sign In
• or
• Sign Up

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  : 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.

This is the hidden content, please

• Sign In
• or
• Sign Up

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  : 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
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  . Or you may refer to the
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up

This is the hidden content, please

• Sign In
• or
• Sign Up

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  : 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.

This is the hidden content, please

• Sign In
• or
• Sign Up

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
This is the hidden content, please Sign In or Sign Up	2 Trillion	4096	Llama-2 excels on English-based market data	This is the hidden content, please Sign In or Sign Up and This is the hidden content, please Sign In or Sign Up	llama-2 consistently shows superior fine-tuning results	Financial Sentiment Analysis, Robo-Advisor
This is the hidden content, please Sign In or Sign Up	1,500B	2048	Maintains high-quality results while being more resource-efficient	This is the hidden content, please Sign In or Sign Up	Good for English market data	Financial Sentiment Analysis
This is the hidden content, please Sign In or Sign Up	1T	2048	MPT models can be trained with high throughput efficiency and stable convergence	This is the hidden content, please Sign In or Sign Up	Good for English market data	Financial Sentiment Analysis
This is the hidden content, please Sign In or Sign Up	366B	2048	World’s largest open multilingual language model	This is the hidden content, please Sign In or Sign Up	Good for English market data	Financial Sentiment Analysis
This is the hidden content, please Sign In or Sign Up	1.4T	32K	Exceptional capability for Chinese language expression	This is the hidden content, please Sign In or Sign Up	Shows prowess for Chinese market data	Financial Sentiment Analysis, Financial Report Summary
This is the hidden content, please Sign In or Sign Up	2.2T	8k	Fast response and high accuracy	This is the hidden content, please Sign In or Sign Up	Effective for Chinese market data	Financial Sentiment Analysis
This is the hidden content, please Sign In or Sign Up	1.8T	8k	Can flexibly and independently construct workflows	This is the hidden content, please Sign In or Sign Up	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
  This is the hidden content, please Sign In or Sign Up	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
  This is the hidden content, please Sign In or Sign Up	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
  This is the hidden content, please Sign In or Sign Up	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
  This is the hidden content, please Sign In or Sign Up	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

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [MIT Technology Review]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [BloombergGPT]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [Finextra]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up

ChatGPT at AI4Finance

• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  , combining ChatGPT and FinRL.
• This is the hidden content, please

  • Sign In
  • or
  • Sign Up

Introductory

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [GPT-4]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [InstructGPT]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  NeurIPS 2022.

This is the hidden content, please

• Sign In
• or
• Sign Up

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

• [GPT-3]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  NeurIPS 2020.
• [GPT-2]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [GPT-1]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [Transformer]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  NeurIPS 2017.

(Financial) Big Data

• [BloombergGPT]

  This is the hidden content, please

  • Sign In
  • or
  • Sign Up

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  A Comprehensive Analysis of Datasets Used to Train GPT-1, GPT-2, GPT-3, GPT-NeoX-20B, Megatron-11B, MT-NLG, and Gopher

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  and paper
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  . Advances in Neural Information Processing Systems, 2022.

• [AI4Finance]

  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  Democratizing Internet-scale financial data.

Interesting Demos

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  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

• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up

Citing FinGPT

News

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [MIT Technology Review]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [BloombergGPT]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [Finextra]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up

ChatGPT at AI4Finance

• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  , combining ChatGPT and FinRL.
• This is the hidden content, please

  • Sign In
  • or
  • Sign Up

Introductory

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [GPT-4]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [InstructGPT]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  NeurIPS 2022.

This is the hidden content, please

• Sign In
• or
• Sign Up

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

• [GPT-3]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  NeurIPS 2020.
• [GPT-2]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [GPT-1]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [Transformer]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  NeurIPS 2017.

(Financial) Big Data

• [BloombergGPT]

  This is the hidden content, please

  • Sign In
  • or
  • Sign Up

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  A Comprehensive Analysis of Datasets Used to Train GPT-1, GPT-2, GPT-3, GPT-NeoX-20B, Megatron-11B, MT-NLG, and Gopher

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  and paper
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  . Advances in Neural Information Processing Systems, 2022.

• [AI4Finance]

  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  Democratizing Internet-scale financial data.

Interesting Demos

• This is the hidden content, please

  • Sign In
  • or
  • Sign Up
  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

• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up
• [YouTube video]
  This is the hidden content, please

  • Sign In
  • or
  • Sign Up

Citing FinGPT

This is the hidden content, please

• Sign In
• or
• Sign Up

 

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.

 

GitHub:

This is the hidden content, please

• Sign In
• or
• Sign Up