metadata

license: apache-2.0
library_name: mlx-llm
language:
  - en
tags:
  - mlx
  - exbert
datasets:
  - bookcorpus
  - wikipedia

BERT base model (uncased) - MLX

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: it does not make a difference between english and English.

Disclaimer: The team releasing BERT did not write a model card for this model so this model card has been written by the Hugging Face team.

Model description

Please, refer to the original model card for more details on bert-base-uncased.

Use it with mlx-llm

Install mlx-llm from GitHub.

git clone https://github.com/riccardomusmeci/mlx-llm
cd mlx-llm
pip install .

Run

from mlx_llm.model import create_model
from transformers import BertTokenizer
import mlx.core as mx

model = create_model("bert-base-uncased") # it will download weights from this repository
tokenizer = BertTokenizer.from_pretrained("bert-large-uncased")

batch = ["This is an example of BERT working on MLX."]
tokens = tokenizer(batch, return_tensors="np", padding=True)
tokens = {key: mx.array(v) for key, v in tokens.items()}

output, pooled = model(**tokens)