marathi-bert-scratch

l3cube-pune/marathi-bert-scratch

marathi-bert-scratch is a fill-mask model from l3cube-pune. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as cc-by-4.0.

MahaBERT is a Marathi BERT model. It is a base-BERT model trained from scratch on L3Cube-MahaCorpus and other publicly available Marathi monolingual datasets. [dataset link] (https://github.com/l3cube-pune/MarathiNLP)

Downloads · 30 days

5% of all-time downloads

All-time downloads

815

Public

Repo size

1.5 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin504 MB · 99%

At a glance

Task: Fill-Mask
Library: transformers
License: cc-by-4.0
Model type: bert
Access: Public
Created: Sep 1, 2022
Updated: Jun 11, 2023
SHA: c61ce446

Datasets

L3Cube-MahaCorpus

Model card

From the Hugging Face model README

MahaBERT-Scratch

More details on the dataset, models, and baseline results can be found in our [paper] (https://arxiv.org/abs/2202.01159)

Best version of this model is available <a href='https://huggingface.co/l3cube-pune/marathi-bert-v2'> here </a>.

@InProceedings{joshi:2022:WILDRE6,
  author    = {Joshi, Raviraj},
  title     = {L3Cube-MahaCorpus and MahaBERT: Marathi Monolingual Corpus, Marathi BERT Language Models, and Resources},
  booktitle      = {Proceedings of The WILDRE-6 Workshop within the 13th Language Resources and Evaluation Conference},
  month          = {June},
  year           = {2022},
  address        = {Marseille, France},
  publisher      = {European Language Resources Association},
  pages     = {97--101}
}

Other Models trained from scratch are listed below: <a href='https://huggingface.co/l3cube-pune/marathi-bert-scratch'> Marathi-Scratch </a> <a href='https://huggingface.co/l3cube-pune/marathi-tweets-bert-scratch'> Marathi-Tweets-Scratch </a> <a href='https://huggingface.co/l3cube-pune/hindi-bert-scratch'> Hindi-Scratch </a> <a href='https://huggingface.co/l3cube-pune/hindi-marathi-dev-bert-scratch'> Dev-Scratch </a> <a href='https://huggingface.co/l3cube-pune/kannada-bert-scratch'> Kannada-Scratch </a> <a href='https://huggingface.co/l3cube-pune/telugu-bert-scratch'> Telugu-Scratch </a> <a href='https://huggingface.co/l3cube-pune/malayalam-bert-scratch'> Malayalam-Scratch </a> <a href='https://huggingface.co/l3cube-pune/gujarati-bert-scratch'> Gujarati-Scratch </a>

Better versions of Monolingual Indic BERT models are listed below: <a href='https://huggingface.co/l3cube-pune/marathi-bert-v2'> Marathi BERT </a> <a href='https://huggingface.co/l3cube-pune/marathi-roberta'> Marathi RoBERTa </a> <a href='https://huggingface.co/l3cube-pune/marathi-albert'> Marathi AlBERT </a>

<a href='https://huggingface.co/l3cube-pune/hindi-bert-v2'> Hindi BERT </a> <a href='https://huggingface.co/l3cube-pune/hindi-roberta'> Hindi RoBERTa </a> <a href='https://huggingface.co/l3cube-pune/hindi-albert'> Hindi AlBERT </a>

<a href='https://huggingface.co/l3cube-pune/hindi-marathi-dev-bert'> Dev BERT </a> <a href='https://huggingface.co/l3cube-pune/hindi-marathi-dev-roberta'> Dev RoBERTa </a> <a href='https://huggingface.co/l3cube-pune/hindi-marathi-dev-albert'> Dev AlBERT </a>

<a href='https://huggingface.co/l3cube-pune/kannada-bert'> Kannada BERT </a> <a href='https://huggingface.co/l3cube-pune/telugu-bert'> Telugu BERT </a> <a href='https://huggingface.co/l3cube-pune/malayalam-bert'> Malayalam BERT </a> <a href='https://huggingface.co/l3cube-pune/tamil-bert'> Tamil BERT </a> <a href='https://huggingface.co/l3cube-pune/gujarati-bert'> Gujarati BERT </a> <a href='https://huggingface.co/l3cube-pune/odia-bert'> Oriya BERT </a> <a href='https://huggingface.co/l3cube-pune/bengali-bert'> Bengali BERT </a> <a href='https://huggingface.co/l3cube-pune/punjabi-bert'> Punjabi BERT </a>

Task: Fill-Mask
Library: transformers
Type: bert
License: cc-by-4.0
Languages: mr
Created: Sep 1, 2022
Updated: Jun 11, 2023