Downloads · 30 days
50
1% of all-time downloads
muril-adapted-local
monsoon-nlp/muril-adapted-local
muril-adapted-local is a fill-mask model from monsoon-nlp. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as apache-2.0.
Multilingual Representations for Indian Languages : Google open sourced this BERT model pre-trained on 17 Indian languages, and their transliterated counterparts.
All-time downloads
4.3K
Public
Parameters
238M
3.8 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin953 MB · 25%
Parameter types
How the weights are stored.
F32238M · 100%
Try a prompt
Model card
From the Hugging Face model README
MuRIL - Unofficial
Multilingual Representations for Indian Languages : Google open sourced this BERT model pre-trained on 17 Indian languages, and their transliterated counterparts.
The model was trained using a self-supervised masked language modeling task. We do whole word masking with a maximum of 80 predictions. The model was trained for 1000K steps, with a batch size of 4096, and a max sequence length of 512.
Original model on TFHub: https://tfhub.dev/google/MuRIL/1
Official release now on HuggingFace (March 2021) https://huggingface.co/google/muril-base-cased
License: Apache 2.0
About this upload
I ported the TFHub .pb model to .h5 and then pytorch_model.bin for compatibility with Transformers.
- Task
- Fill-Mask
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- en, hi, bn, ta, as, gu
- Created
- Mar 2, 2022
- Updated
- Sep 3, 2023