BloombergGPT
Bloomberg
Bloomberg's 50-billion parameter large language model trained specifically on financial data. BloombergGPT was trained on 363 billion tokens of financial text — news, filings, research, and Bloomberg Terminal data — delivering superior performance on financial NLP tasks like sentiment analysis, named entity recognition, and question answering.
Key Features
- Finance-specific 50B parameter model
- 363B tokens of financial training data
- Superior financial sentiment analysis
- Bloomberg Terminal data integration
Statistics
User Reviews
"BloombergGPT understands financial terminology and context at a level no general model comes close to. For financial NLP tasks it's in a class of its own."
"BloombergGPT, hiçbir genel modelin yaklaşamadığı bir düzeyde finansal terminolojiyi ve bağlamı anlıyor. Finansal NLP görevleri için kendi sınıfında."
"BloombergGPT versteht Finanzterminologie auf einem Niveau, das kein allgemeines Modell erreicht. Für Finanz-NLP ist es in einer eigenen Klasse."