Bert Base Uncased

🚀 BERT base model (uncased)

A pre - trained English language model using masked language modeling (MLM) objective.

🚀 Quick Start

To start using the model, first download it by cloning the repository:

git clone https://huggingface.co/OWG/bert-base-uncased

Then, you can utilize the model with the following Python code:

from onnxruntime import InferenceSession, SessionOptions, GraphOptimizationLevel
from transformers import BertTokenizer


tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")

options = SessionOptions()
options.graph_optimization_level = GraphOptimizationLevel.ORT_ENABLE_ALL

session = InferenceSession("path/to/model.onnx", sess_options=options)
session.disable_fallback()

text = "Replace me by any text you want to encode."
input_ids = tokenizer(text, return_tensors="pt", return_attention_mask=True)

inputs = {k: v.cpu().detach().numpy() for k, v in input_ids.items()}
outputs_name = session.get_outputs()[0].name

outputs = session.run(output_names=[outputs_name], input_feed=inputs)

✨ Features

• Pretrained on English: This model is pretrained on English language using a masked language modeling (MLM) objective.
• Uncased: It does not distinguish between uppercase and lowercase letters, e.g., it treats "english" and "English" the same.

📦 Installation

You can download the model by cloning the repository:

git clone https://huggingface.co/OWG/bert-base-uncased

💻 Usage Examples

Basic Usage

from onnxruntime import InferenceSession, SessionOptions, GraphOptimizationLevel
from transformers import BertTokenizer


tokenizer = BertTokenizer.from_pretrained("bert-base-uncased")

options = SessionOptions()
options.graph_optimization_level = GraphOptimizationLevel.ORT_ENABLE_ALL

session = InferenceSession("path/to/model.onnx", sess_options=options)
session.disable_fallback()

text = "Replace me by any text you want to encode."
input_ids = tokenizer(text, return_tensors="pt", return_attention_mask=True)

inputs = {k: v.cpu().detach().numpy() for k, v in input_ids.items()}
outputs_name = session.get_outputs()[0].name

outputs = session.run(output_names=[outputs_name], input_feed=inputs)

📚 Documentation

Model description

This is a pretrained model on English language using a masked language modeling (MLM) objective. It was introduced in this paper and first released in this repository. This model is uncased, meaning it does not make a difference between "english" and "English".

Original implementation

Follow this link to see the original implementation.

📄 License

This model is licensed under the Apache 2.0 license.