README.md

metadata

language: en
tags:
  - bert
  - classification
  - pytorch
pipeline_tag: text-classification

BiEncoder Classification Model

This model is a BiEncoder architecture based on BERT for text pair classification.

Model Details

• Base Model: bert-base-uncased
• Architecture: BiEncoder with BERT base
• Number of classes: 4

Usage

from transformers import AutoTokenizer
import torch

# Load tokenizer
tokenizer = AutoTokenizer.from_pretrained("minoosh/bert-clf-biencoder-cross_entropy")

# Load model weights
state_dict = torch.load("pytorch_model.bin")

# Initialize model (you'll need the BiEncoderModel class)
model = BiEncoderModel(
    base_model=AutoModel.from_pretrained("bert-base-uncased"),
    num_classes=4
)
model.load_state_dict(state_dict)