Sukuna404/modernbert-emotion-qat-int8

ModernBERT Emotion Detection — QAT INT8

Fine-tuned and quantized version of answerdotai/ModernBERT-base for 6-class emotion classification using the dair-ai/emotion dataset.

Quantization

• Method: INT8 weight-only quantization via torchao
• Weights: INT8
• Activations: FP32
• Speedup: ~2x faster on CPU vs FP32

Labels

ID	Label
0	sadness
1	joy
2	love
3	anger
4	fear
5	surprise

Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("Sukuna404/modernbert-emotion-qat-int8")
model = AutoModelForSequenceClassification.from_pretrained(
    "Sukuna404/modernbert-emotion-qat-int8"
)
model.eval()

def predict(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)
    with torch.no_grad():
        outputs = model(**inputs)
    pred_id = outputs.logits.argmax().item()
    return model.config.id2label[pred_id]

print(predict("I am so happy today!"))  # joy