Instructions to use ddrg/math_structure_bert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ddrg/math_structure_bert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ddrg/math_structure_bert")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("ddrg/math_structure_bert") model = AutoModel.from_pretrained("ddrg/math_structure_bert", device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
datasets:
- ddrg/math_formulas
- ddrg/math_formula_retrieval
- ddrg/math_text
- ddrg/named_math_formulas
Mathematical Structure Aware BERT
Pretrained model based on bert-base-cased with further mathematical pre-training.
Compared to bert-base-cased, 300 additional mathematical LaTeX tokens have been added before the mathematical pre-training.