Downloads · 30 days
11
3% of all-time downloads
microbert-tamil-mx
lgessler/microbert-tamil-mx
microbert-tamil-mx is a feature extraction model from lgessler. Use it when you need embeddings to search or compare text. It is set up for transformers.
All-time downloads
387
Public
Repo size
13.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin6.7 MB · 93%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Dec 23, 2022
- Updated
- Dec 23, 2022
- SHA
- f51a7b65
Try a prompt
Model card
From the Hugging Face model README
This is a MicroBERT model for Tamil.
- Its suffix is -mx, which means that it was pretrained using supervision from masked language modeling and XPOS tagging.
- The unlabeled Tamil data was taken from a June 2022 dump of Tamil Wikipedia, downsampled to 1,429,735 tokens.
- The UD treebank UD_Tamil-TTB, v2.9, totaling 9,581 tokens, was used for labeled data.
Please see the repository and the paper for more details.
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- Languages
- tam
- Created
- Dec 23, 2022
- Updated
- Dec 23, 2022