FinGPT<T>

Models & Types · AiDotNet.Finance.NLP

FinGPT neural network model for domain-specific financial language generation and analysis.

Inheritance: NeuralNetworkBase<T> → FinancialModelBase<T> → FinancialNLPModelBase<T> → FinGPT<T>

For Beginners

FinGPT is an open-source financial language model that can analyze news, generate financial reports, and perform sentiment analysis. Unlike proprietary models like BloombergGPT, FinGPT is designed to be accessible and fine-tunable by anyone. It can be adapted to specific financial tasks like stock prediction from news headlines or risk assessment from annual reports.

Example

// Define architecture for open-source financial language generation (2048 tokens)
var architecture = new NeuralNetworkArchitecture<double>(
    inputType: InputType.OneDimensional,
    taskType: NeuralNetworkTaskType.MultiClassClassification,
    inputHeight: 2048, inputWidth: 1, inputDepth: 1, outputSize: 32000);
            
// Training mode: fine-tunable decoder for financial text generation and analysis
var model = new FinGPT<double>(architecture);
            
// ONNX inference mode: load pre-trained FinGPT model
var onnxModel = new FinGPT<double>(architecture, "fingpt.onnx");

Constructors

Constructor Summary
FinGPT(NeuralNetworkArchitecture<T> architecture, FinGPTOptions<T> options, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer, ILossFunction<T> lossFunction) Creates a FinGPT network in native mode for training.
FinGPT(NeuralNetworkArchitecture<T> architecture, string onnxModelPath, FinGPTOptions<T> options, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer) Creates a FinGPT network in native mode for training.