bert and BERT-keras

bert
51
Established
BERT-keras
44
Emerging
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 25/25
Maintenance 0/25
Adoption 10/25
Maturity 9/25
Community 25/25
Stars: 39,918
Forks: 9,711
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 815
Forks: 191
Downloads:
Commits (30d): 0
Language: Python
License: GPL-3.0
Archived Stale 6m No Package No Dependents
Archived Stale 6m No Package No Dependents

About bert

google-research/bert

TensorFlow code and pre-trained models for BERT

Provides 24 compact model variants (2-12 layers, 128-768 hidden units) optimized for resource-constrained environments, validated on GLUE benchmarks with knowledge distillation support. Introduces Whole Word Masking during pre-training to improve token prediction difficulty and features TensorFlow Hub integration for streamlined fine-tuning across downstream NLP tasks like text classification and semantic similarity.

About BERT-keras

Separius/BERT-keras

Keras implementation of BERT with pre-trained weights

Scores updated daily from GitHub, PyPI, and npm data. How scores work