Downloads · 30 days
44
6% of all-time downloads
Raviraj/xlm-roberta-large-MLMfintune-hi-fraudcall
xlm-roberta-large-MLMfintune-hi-fraudcall is a fill-mask model from Raviraj. Use it when you need the model to fill a missing word. It is set up for transformers.
This model is finetuned for masked language modeling.
Downloads · 30 days
44
6% of all-time downloads
All-time downloads
678
Public
Parameters
560M
4.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.bin2.2 GB · 50%
How the weights are stored.
F32560M · 100%
From the Hugging Face model README
This model is finetuned for masked language modeling.
I have used xlm-roberta-large model for pretraining over half a million tokens of
Hindi fraud call transcripts.
You can import this model with pretrained() method from the transformer library.
please note this works well on general Hindi but it's result on native language dialogues are enhanced
in comparison to general libraries.