Instructions to use AISystems/PAK-LEGAL-BERT-small-uncased with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AISystems/PAK-LEGAL-BERT-small-uncased with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="AISystems/PAK-LEGAL-BERT-small-uncased")# Load model directly from transformers import AutoTokenizer, AutoModelForPreTraining tokenizer = AutoTokenizer.from_pretrained("AISystems/PAK-LEGAL-BERT-small-uncased") model = AutoModelForPreTraining.from_pretrained("AISystems/PAK-LEGAL-BERT-small-uncased") - Notebooks
- Google Colab
- Kaggle
Model
This is a bert model that is trained on 10GB of Pakistan-Legal-Corpus on NSP and MLM tasks by AI SYSTEMS.
Model Details
This model was orignally taken from "legal-bert-small-uncased" (https://huggingface.co/nlpaueb/legal-bert-small-uncased) and was further pretrained using the original Bert paper for NSP amd MLM task.
- Downloads last month
- 4