Distilbert Base Uncased Mnli

🚀 ONNX convert typeform/distilbert-base-uncased-mnli

This project focuses on converting the typeform/distilbert-base-uncased-mnli model to ONNX format. It provides a zero - shot classification solution using a fine - tuned DistilBERT model.

🚀 Quick Start

The model used here is an uncased DistilBERT model that has been fine - tuned on the Multi - Genre Natural Language Inference (MNLI) dataset for zero - shot classification. It is case - insensitive, meaning it treats "english" and "English" the same.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

No code examples are provided in the original document.

📚 Documentation

Conversion of typeform/distilbert-base-uncased-mnli

This is the uncased DistilBERT model fine - tuned on Multi - Genre Natural Language Inference (MNLI) dataset for the zero - shot classification task. The model is not case - sensitive, i.e., it does not make a difference between "english" and "English".

Training

Training is done on a p3.2xlarge AWS EC2 instance (1 NVIDIA Tesla V100 GPUs), with the following hyperparameters:

$ run_glue.py \
    --model_name_or_path distilbert-base-uncased \
    --task_name mnli \
    --do_train \
    --do_eval \
    --max_seq_length 128 \
    --per_device_train_batch_size 16 \
    --learning_rate 2e-5 \
    --num_train_epochs 5 \
    --output_dir /tmp/distilbert-base-uncased_mnli/

Evaluation results

🔧 Technical Details

The model is based on the DistilBERT architecture, which is a distilled version of BERT. It is fine - tuned on the MNLI dataset for zero - shot classification. The training is performed on a specific AWS EC2 instance with defined hyperparameters.

📄 License

No license information is provided in the original document.