# FinGPT: Open-Source Financial Large Language Models
[](https://pepy.tech/project/fingpt)
[](https://pepy.tech/project/fingpt)
[](https://www.python.org/downloads/release/python-360/)
[](https://pypi.org/project/fingpt/)
<div align="center">
<img align="center" src=figs/logo_transparent_background.png width="40%"/>
</div>
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://arxiv.org/abs/2306.06031)
<https://huggingface.co/FinGPT>
[](https://discord.gg/trsr8SXpW5)
## What's New:
- [Model Release] Nov, 2023: We release [FinGPT-Forecaster](https://github.com/AI4Finance-Foundation/FinGPT/tree/master/fingpt/FinGPT_Forecaster)! ð¥[Demo](https://huggingface.co/spaces/FinGPT/FinGPT-Forecaster), [Medium Blog](https://medium.datadriveninvestor.com/introducing-fingpt-forecaster-the-future-of-robo-advisory-services-50add34e3d3c) & [Model](https://huggingface.co/FinGPT/fingpt-forecaster_dow30_llama2-7b_lora) are available on Huggingfaceð¤!
- [Paper Acceptance] Oct, 2023: ["FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets"](https://arxiv.org/abs/2310.04793) is acceptedð by [Instruction Workshop](https://an-instructive-workshop.github.io/) @ NeurIPS 2023
- [Paper Acceptance] Oct, 2023: ["FinGPT: Democratizing Internet-scale Data for Financial Large Language Models"](https://arxiv.org/abs/2307.10485) is acceptedð by [Instruction Workshop](https://an-instructive-workshop.github.io/) @ NeurIPS 2023
- [Model Release] Oct, 2023: We release the [financial multi-task LLMs](https://huggingface.co/FinGPT) ð¥ produced when evaluating base-LLMs on [FinGPT-Benchmark](https://github.com/AI4Finance-Foundation/FinGPT/tree/master/fingpt/FinGPT_Benchmark)
- [Paper Acceptance] Sep, 2023: ["Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models"](https://arxiv.org/abs/2310.04027) is acceptedð by [ACM International Conference on AI in Finance (ICAIF-23)](https://ai-finance.org/icaif-23-accepted-papers/)
- [Model Release] Aug, 2023: We release the [financial sentiment analysis model](https://huggingface.co/FinGPT/fingpt-sentiment_llama2-13b_lora) ð¥
- [Paper Acceptance] Jul, 2023: ["Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models"](https://arxiv.org/abs/2306.12659) is acceptedð by [FinLLM 2023](https://finllm.github.io/workshop/#/fcb)@IJCAI 2023
- [Paper Acceptance] Jul, 2023: ["FinGPT: Open-Source Financial Large Language Models"](https://arxiv.org/abs/2306.06031) is acceptedð by [FinLLM 2023](https://finllm.github.io/workshop/#/fcb)@IJCAI 2023
- [Medium Blog] Jun 2023: [FinGPT: Powering the Future of Finance with 20 Cutting-Edge Applications](https://medium.datadriveninvestor.com/fingpt-powering-the-future-of-finance-with-20-cutting-edge-applications-7c4d082ad3d8)
## Why FinGPT?
1). Finance is highly dynamic. [BloombergGPT](https://arxiv.org/abs/2303.17564) 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](https://huggingface.co/spaces/FinGPT/FinGPT-Forecaster)
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 Submitï¼ 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](https://github.com/AI4Finance-Foundation/FinGPT/tree/master/fingpt/FinGPT_Forecaster)
## FinGPT Demos:
### Current State-of-the-arts for Financial Sentiment Analysis
* [FinGPT V3 (Updated on 10/12/2023)](./fingpt)
* 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](https://huggingface.co/FinGPT/fingpt-sentiment_llama2-13b_lora) 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](https://huggingface.co/FinGPT/fingpt-sentiment_llama2-13b_lora)| **0.882** | 0.874 | **0.903** | **0.643** | 1 Ã RTX 3090 | 17.25 hours | $17.25 |
| FinGPT v3.2| 0.850 | 0.860 | 0.894 | 0.636 | 1 Ã A100 | 5.5 hours | $ 22.55 |
| FinGPT v3.1| 0.855 | 0.850 | 0.875 | 0.642 | 1 Ã A100 | 5.5 hours | $ 22.55 |
| FinGPT (8bit) | 0.855 | 0.847 | 0.879 | 0.632 | 1 Ã RTX 3090 | 6.47 hours | $ 6.47 |
| FinGPT (QLoRA) | 0.777 | 0.752 | 0.828 | 0.583 | 1 Ã 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 Ã NVIDIA K80 GPU | - | - |
| Llama2-7B | 0.390 | 0.800 | 0.296 | 0.503 | 2048 Ã A100 | 21 days | $ 4.23 million |
| BloombergGPT | 0.511 | 0.751 | - | - | 512 Ã A100 | 53 days | $ 2.67 million
金融大型语言模型：FinGPT
版权申诉
156 浏览量
2024-01-12
11:27:15
上传
评论 1
收藏 9.82MB ZIP 举报
金融大型语言模型：FinGPT （235个子文件） 
df.csv 2.33MB ChatGPT_Robo_Advisor_v2_Results.csv 434KB sent_valid_penultimate_run_classified_classified.csv 234KB sent_valid_penultimate_run.csv 233KB sent_valid_penultimate_run_classified.csv 233KB sent_valid_scraped.csv 212KB sent_valid.csv 212KB maotai.csv 44KB maotai_another.csv 37KB hs_300.csv 33KB ChatGPT_Robo_Advisor_Results.csv 30KB test_classified.csv 25KB test.csv 25KB dataset.csv 11KB dataset.csv 7KB .env.example 130B .gitignore 2KB .gitignore 47B FinGPT_Training_LoRA_with_ChatGLM2_6B_for_Beginners.ipynb 731KB trade_with_gpt3.ipynb 666KB demo.ipynb 626KB FinGPT_Inference_Llama2_13B_falcon_7B_for_Beginners.ipynb 223KB load_data.ipynb 154KB prepare_data.ipynb 111KB infer.ipynb 101KB ChatGPT_Robo_Advisor_v2.ipynb 64KB prepare_data.ipynb 64KB trade_with_chatgpt.ipynb 52KB make_dataset_by_date.ipynb 51KB FMP.ipynb 46KB get_chatgpt_results.ipynb 40KB demo.ipynb 34KB train_Llama2_13B.ipynb 23KB main.ipynb 19KB ChatGPT_Robo_Advisor.ipynb 18KB train_ChatGLM2_6B.ipynb 18KB main.ipynb 18KB making_data.ipynb 18KB train.ipynb 15KB benchmarks.ipynb 12KB benchmarks_llama2_13b.ipynb 11KB SeekingAlpha_Content.ipynb 9KB download_content_demo.ipynb 9KB ChatGPT_sentiment_analysis_benchmark.ipynb 8KB
framework.jpg 521KB instruction_following_dataset.jpg 393KB white_logo_color_background.jpg 321KB FinGPT.jpg 141KB config_new.json 810B config.json 793B config.json 784B config.json 784B config_hf.json 222B LICENSE 1KB README.md 29KB README.md 17KB README.md 14KB readme.md 6KB README.md 5KB README.md 5KB readme.md 5KB CODE_OF_CONDUCT.md 4KB README.md 4KB README.md 4KB readme.md 4KB README.md 3KB CONTRIBUTING.md 3KB README.md 3KB README.md 2KB README.md 2KB readme.md 2KB README.md 1KB feature_request.md 595B README.md 360B README.md 199B README.md 193B README.md 8B nohup.out 6KB text-curie-001.pkl 1.9MB text-davinci-003.pkl 1.47MB
FinGPT_Benchmark_20231110.png 1004KB FinGPT_RAG_framework.png 875KB FinGPT_Benchmark_update1.png 824KB FinGPT_Benchmark.png 821KB FinGPT_framework_20231003.png 794KB FinGPT_framework.png 679KB FinGPT_FinNLP_data_source.png 365KB fingpt_best_presentation.png 238KB logo_transparent_background.png 208KB interface.png 167KB showcase.png 131KB output.png 105KB response.png 66KB title.png 19KB plotting.py 62KB tears.py 46KB timeseries.py 36KB news_scraper.py 29KB raw_datasets.py 26KB perf_attrib.py 22KB共 235 条
- 1
- 2
- 3
资源评论
