1
→
AI4Finance-Foundation/FinGPT
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
About AI4Finance-Foundation/FinGPT
AI4Finance-Foundation/FinGPT is an open-source project on GitHub, mainly written in Jupyter Notebook. FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace. It currently holds 21,271 stars and 3,013 forks with 0 open issues, and was last pushed on an unknown date (repository created unknown).
Project Overview
AI Homed tracks it on the AI Prompt Engineering board, currently at rank #62 with 8 new stars today.
GitHub Repository Details
README
FinGPT: Open-Source Financial Large Language Models
Let us not expect Wall Street to open-source LLMs or open APIs, due to FinTech institutes' internal regulations and policies.
Project Contributors
FinGPT is an open-source financial large language model project developed and maintained by the AI4Finance Foundation.
Key contributors include:
- Hongyang (Bruce) Yang – research and development on financial large language models and related applications
- [other contributors…]
What's New:
- [Model Release] Nov, 2023: We release FinGPT-Forecaster! 🔥Demo, Medium Blog & Model are available on Huggingface🤗!
- [Paper Acceptance] Oct, 2023: "FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets" is accepted🎉 by Instruction Workshop @ NeurIPS 2023
- [Paper Acceptance] Oct, 2023: "FinGPT: Democratizing Internet-scale Data for Financial Large Language Models" is accepted🎉 by Instruction Workshop @ NeurIPS 2023
- [Model Release] Oct, 2023: We release the financial multi-task LLMs 🔥 produced when evaluating base-LLMs on FinGPT-Benchmark
- [Paper Acceptance] Sep, 2023: "Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models" is accepted🎉 by ACM International Conference on AI in Finance (ICAIF-23)
- [Model Release] Aug, 2023: We release the financial sentiment analysis model 🔥
- [Paper Acceptance] Jul, 2023: "Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models" is accepted🎉 by FinLLM 2023@IJCAI 2023
- [Paper Acceptance] Jul, 2023: "FinGPT: Open-Source Financial Large Language Models" is accepted🎉 by FinLLM 2023@IJCAI 2023
- [Medium Blog] Jun 2023: FinGPT: Powering the Future of Finance with 20 Cutting-Edge Applications
Quick Start
🚀 Get started with FinGPT in minutes!
For detailed setup instructions for running FinGPT locally or on Replit, including hardware requirements and troubleshooting, check out our comprehensive SETUP Guide.
❓ Have questions? Check our FAQ for answers to common questions about FinGPT usage, capabilities, and limitations.
Installation
# Clone the repository
git clone https://github.com/AI4Finance-Foundation/FinGPT.git
cd FinGPT
Install dependencies
pip install -r requirements.txt
pip install -e .
Try the Demo
Visit our HuggingFace Space to try FinGPT-Forecaster without any installation!
Basic Usage
# Using cloud API (no GPU required)
import os
os.environ['FINGPT_LLM_PROVIDER'] = 'openai'
Using local models (requires GPU)
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
See SETUP.md for detailed examples
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
Market Support: FinGPT-Forecaster is currently trained on US market data (DOW 30). For other markets (including China stock market), you would need to: 1. Collect appropriate market data 2. Fine-tune the model on the target market data 3. Consider using FinGPT v1.x models which were designed for Chinese markets 4. Adapt the data pipeline and model architecture for specific market characteristics
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 F1 | FPB | FiQA-SA | TFNS | NWGI | Devices | Time | Cost |
- 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
Instruction Tuning Datasets and Models
The datasets we used, and the multi-task financial LLM models are available atOur Code | 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 Instructions | | 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|
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 | | --------- | --------------------- |---------------- | | fingpt-mt_llama2-7b_lora| Fine-tuned Llama2-7b model with LoRA | Multi-Task | | fingpt-mt_falcon-7b_lora| Fine-tuned falcon-7b model with LoRA | Multi-Task | | fingpt-mt_bloom-7b1_lora | Fine-tuned bloom-7b1 model with LoRA | Multi-Task | | fingpt-mt_mpt-7b_lora | Fine-tuned mpt-7b model with LoRA | Multi-Task | | fingpt-mt_chatglm2-6b_lora | Fine-tuned chatglm-6b model with LoRA | Multi-Task | | fingpt-mt_qwen-7b_lora | Fine-tuned qwen-7b model with LoRA | Multi-Task | | fingpt-sentiment_llama2-13b_lora | Fine-tuned llama2-13b model with LoRA | Single-Task | | fingpt-forecaster_dow30_llama2-7b_lora | Fine-tuned llama2-7b model with LoRA | Single-Task |
Tutorials
[[Training] Beginner’s Guide to FinGPT: Training with LoRA and ChatGLM2–6B One Notebook, $10 GPU](https://byfintech.medium.com/beginners-guide-to-fingpt-training-with-lora-chatglm2-6b-9eb5ace7fe99)Understanding FinGPT: An Educational Blog Series
+ FinGPT: Powering the Future of Finance with 20 Cutting-Edge Applications + FinGPT I: Why We Built the First Open-Source Large Language Model for Finance + FinGPT II: Cracking the Financial Sentiment Analysis Task Using Instruction Tuning of General-Purpose Large Language ModelsFinGPT 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.
Cloud LLM Providers for FinGPT Inference
For the Finogrid platform (finogrid/), FinGPT supports multiple cloud LLM providers as alternatives to running local models. Set FINGPT_LLM_PROVIDER in your environment:
| Provider | Model | Context Length | Use Case | |----------|-------|---------------|----------| | OpenAI | GPT-3.5-turbo | 16K | Default fallback for sentiment & agents | | MiniMax | MiniMax-M3 | 512K | Latest flagship model with 128K max output and image input support | | FinGPT (local) | Llama-2-13B LoRA | 4K | Full local inference (requires GPU) |
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.
- Benchmark Results for the above open-source Base Models in the financial sentiment analysis task using the same instruction template for SFT (LoRA):
All Thanks To Our Contributors :
GitHub Stars & Activity
21,271Stars
3,013Forks
0Open issues
Jupyter NotebookLanguage
GitHub Popularity
GitHub stars21,271
Forks3,013
Open issues0
Primary languageJupyter Notebook
License-
Stars gained today8
Created-
Last pushed-
Trending History
Daily boardrank #62 · ▲ 8 stars
Related AI Projects
→2
→3
→4
→5
→6
→7
→8
→