Fill-Mask
Transformers
Safetensors
English
ultrabert
encoder
masked-language-modeling
long-context
custom_code
Instructions to use dmis-lab/UltraBERT-150M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmis-lab/UltraBERT-150M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="dmis-lab/UltraBERT-150M", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("dmis-lab/UltraBERT-150M", trust_remote_code=True) model = AutoModelForMaskedLM.from_pretrained("dmis-lab/UltraBERT-150M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download head_50%.pth from dmis-lab/UltraBERT-150M: direct link, hf CLI and curl.
- Browser
- Download file 156 MB
-
https://huggingface.co/dmis-lab/UltraBERT-150M/resolve/main/head_50%25.pth
- Command line
-
hf download hf://dmis-lab/UltraBERT-150M/head_50%.pth
-
curl -L -o head_50%.pth https://huggingface.co/dmis-lab/UltraBERT-150M/resolve/main/head_50%25.pth
156 MB
- Xet hash:
- e264761d697788944fb0dc991a3ab354543a0fb82deade7f513eadd6cf2de98b
- Size of remote file:
- 156 MB
- SHA256:
- b398813e4298bb1efdc9cb81b927e260afc020645ca9679c891b2c04fd08e41a
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.