NOSIBLE/financial-sentiment-v1.1-base
TEXT GENERATIONConcurrency Cost:1Model Size:0.8BQuant:BF16Ctx Length:32kPublished:Nov 25, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Warm

NOSIBLE/financial-sentiment-v1.1-base is a 0.8 billion parameter financial sentiment classification model developed by NOSIBLE, fine-tuned from Qwen3-0.6B. It is designed to determine positive, neutral, or negative financial impact from short text snippets. This model excels at classifying real-world, noisy financial text, outperforming FinBERT on the Financial PhraseBank dataset despite not being trained on it. Its primary use case is accurate and efficient financial sentiment analysis in production settings.

Loading preview...