# AI4Finance-Foundation/FinGPT

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

Repository: https://github.com/AI4Finance-Foundation/FinGPT
Canonical: https://ross.abutalabs.com/products/fingpt
Homepage: https://fingpt.io
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: chatgpt, finance, fintech, large-language-models, machine-learning, nlp, prompt-engineering, pytorch, reinforcement-learning, robo-advisor, sentiment-analysis, technical-analysis, fingpt
Last push: 2026-08-02T03:23:48+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 46, longevity 92
- inputs: {"age_days": 1299, "days_push": 31, "days_rel": 147, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21154, forks 3001 (observed 2026-08-28T04:11:30.607285+00:00)

## What it is
FinGPT is an open-source financial large language model project from the AI4Finance Foundation, providing domain-tuned models, fine-tuning datasets, and APIs for financial NLP tasks like sentiment analysis and forecasting. It includes notebooks, benchmarks, and HuggingFace-hosted models for building financial AI applications.

## Use cases
- analyze sentiment of financial news and filings
- forecast stock price movements with LLMs
- fine-tune an LLM on financial datasets
- query SEC filings with natural language
- build a robo-advisor chatbot
- benchmark LLMs on financial tasks

## When to choose
- you need open-source financial NLP models instead of closed APIs
- you want to fine-tune LLMs on financial data cheaply
- you're doing academic research on financial LLMs

## When to avoid
- you need production-grade regulated trading infrastructure
- you want a turnkey commercial robo-advisor with support
- your task is general-purpose NLP outside finance

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, nlp, llm-training, rag, prompt-engineering
- domain: fintech, large-language-models, machine-learning
- platform: python, cross-platform
- tags: financial-llm, sentiment-analysis, robo-advisor, fine-tuning, huggingface, fintech, forecasting, natural-language-processing, finance

## Member repositories
- AI4Finance-Foundation/FinGPT (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:30.607285+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:58:29.053860+00:00, confidence not recorded.
  - readme: https://github.com/AI4Finance-Foundation/FinGPT (fetched 2026-08-28T04:11:30.607285+00:00, sha 36e2a898fade)
  - homepage: https://fingpt.io (fetched 2026-08-29T07:57:01.174072+00:00, sha fe860e40227a)
  - site_page: https://fingpt.io/docs (fetched 2026-08-29T07:57:01.183419+00:00, sha 7415adead5ab)
  - registry_pypi: https://pypi.org/pypi/fingpt/json (fetched 2026-08-29T07:57:01.185255+00:00, sha 9d1950982960)
- Data as of 2026-08-30T08:39:29.467469+00:00.