BERT (bert_large_uncased)

A pure Keras 3 port of BERT, converted from google-bert/bert-large-uncased (Hugging Face Transformers).

The weights are backend-agnostic: the same checkpoint loads and runs identically under the JAX, TensorFlow, or PyTorch Keras backend (KERAS_BACKEND=jax|tensorflow|torch), via kerasformers.

Usage

from kerasformers.models.bert import BertModel

model = BertModel.from_weights("kerasformers/bert_large_uncased")

Downloads last month: -

Model tree for kerasformers/bert_large_uncased

Base model

google-bert/bert-large-uncased

Finetuned

(175)

this model

Collection including kerasformers/bert_large_uncased

BERT

Collection

Pure Keras 3, backend-agnostic (JAX / TensorFlow / PyTorch) ports of BERT encoders and masked-LM heads. • 4 items • Updated about 3 hours ago