OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Fingpt

FinGPT is an open-source collection of financial large language models from the AI4Finance Foundation, with trained models released on Hugging Face for finance-related natural-language-processing work.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Fingpt — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use FinGPT when an open, finance-focused model collection is a suitable starting point for research or application development and you can select and configure an appropriate released model.

Who it is for

  • AI and machine-learning researchers working with financial text
  • Developers building finance-focused NLP prototypes
  • Teams evaluating open financial language models

Documented uses

  • Analyze sentiment in financial text
  • Prototype finance-focused question-answering systems
  • Research financial natural-language-processing tasks
  • Explore robo-advisor prototypes with appropriate domain validation and safety review
Before you choose

Requirements & limits

The repository is public and MIT licensed. It documents both local-model use with a GPU and cloud-model use without a GPU; the Hugging Face FinGPT-Forecaster demo is presented as an installation-free way to try that release.

  • Model selection matters because FinGPT publishes multiple finance-oriented releases, including sentiment and Forecaster models.
  • The project supports both cloud and self-hosted patterns, with different hardware implications described for each.
  • The repository uses Hugging Face releases and identifies PyTorch among its project topics.
  • The available repository evidence does not specify one general inference interface or a complete deployment requirement set.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the FinGPT repository

Prepare a local FinGPT project environment using the installation stages documented in the repository.

Before you start

  • A local environment capable of cloning the public repository.
  • The repository’s requirements file and package installation process.

Steps

  1. Clone the FinGPT repository.

  2. Change into the repository directory.

  3. Install the dependencies from requirements.txt.

  4. Install the project in editable mode.

Expected outcome

The FinGPT project is installed according to the repository’s documented installation sequence.

Guide limitations

  • This setup sequence does not document a complete model-inference workflow.
  • The repository directs readers to SETUP.md for detailed hardware requirements and troubleshooting.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
AI4Finance-Foundation/FinGPT · Official homepage title · retained in its source language
How we review sourcesSuggest a correction