deberta-v3-emotion-multilabel

DeBERTa V3 - Multi-label Emotion Classifier

This model is a fine-tuned version of microsoft/deberta-v3-base for multi-label emotion classification.

Model Details

• Base model: DeBERTa V3
• Task: Multi-label emotion detection
• Architecture: DebertaV2ForSequenceClassification
• Number of labels: 14
• Format: safetensors

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("PuroFuro/deberta-v3-emotion-multilabel")
model = AutoModelForSequenceClassification.from_pretrained("PuroFuro/deberta-v3-emotion-multilabel")

inputs = tokenizer("I feel nervous but hopeful.", return_tensors="pt")
outputs = model(**inputs)
probs = torch.sigmoid(outputs.logits)
print(probs)