achen0525/DistilBERT_FOMC_Classifier

Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. --> Fine-Tuned Transformer for FOMC Sentiment Classification

Model Details

Model Description

<!-- Provide a longer summary of what this model is. -->

This model is a fine-tuned version of DistilBERT for FOMC meeting sentiment classification. It predicts whether a sentence from U.S. Federal Open Market Committee (FOMC) statements is Dovish, Hawkish, or Neutral.

• —Developed by: [Ao Chen]
• —Model type: [Encoder-only Transformer (DistilBERT)]
• —Language(s) (NLP): [en]
• —License: [Apache 2.0]
• —Finetuned from model [optional]: [distilbert-base-uncased]

Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_name = "achen0525/DistilBERT_FOMC_Classifier"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

text = "The Committee decided to maintain the target range for the federal funds rate."
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)
pred = torch.argmax(outputs.logits, dim=1)

labels = ['Dovish', 'Hawkish', 'Neutral']
print(labels[pred.item()])

Model Card Contact

For questions or feedback, reach out to: aochen@bu.edu