How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("feature-extraction", model="DeepWokLab/bert-tiny")
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("DeepWokLab/bert-tiny")
model = AutoModel.from_pretrained("DeepWokLab/bert-tiny", device_map="auto")
Quick Links

BERT-Tiny

This checkpoint was originally from Google's BERT repository, and was converted to HuggingFace format by prajjwal1/bert-tiny.

We forces contiguous tensors in the state_dict and uploaded here for MASE and Advanced Deep Learning System Lab.

Downloads last month
17
Safetensors
Model size
4.39M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support