neoyipeng/ModernFinBERT-base

ModernFinBERT: Financial Sentiment Analysis

ModernFinBERT is a financial sentiment analysis model based on the ModernBERT architecture, fine-tuned specifically for financial text classification.

Model Details

• Base Model: answerdotai/ModernBERT-base
• Task: 3-class sentiment classification (Negative, Neutral, Positive)
• Training Data: Financial text from multiple sources (excluding FinancialPhraseBank for evaluation)
• Parameters: 149,607,171

Performance

• FinancialPhraseBank Accuracy: 90.47%
• Target: >94% accuracy on FinancialPhraseBank

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("neoyipeng/ModernFinBERT-base")
model = AutoModelForSequenceClassification.from_pretrained("neoyipeng/ModernFinBERT-base")

text = "The company's quarterly results exceeded analyst expectations."
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)

labels = ["NEGATIVE", "NEUTRAL", "POSITIVE"] 
predicted_class = labels[predictions.argmax().item()]
confidence = predictions.max().item()

print(f"Sentiment: {predicted_class} ({confidence:.2f})")

Training Details

• Epochs: 10
• Batch Size: 32
• Learning Rate: 5e-5
• Optimizer: AdamW
• Scheduler: Cosine
• Framework: Unsloth + Transformers

Citation

If you use this model, please cite:

@misc{modernfinbert2025,
  title={ModernFinBERT: A Modern Approach to Financial Sentiment Analysis},
  author={Neo Yi Peng},
  year={2025},
  howpublished={HuggingFace Model Hub},
  url={https://huggingface.co/neoyipeng/ModernFinBERT-base}
}