Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
anwesham
/
indic_with_mbert_tokens
like
0
Model card
Files
Files and versions
xet
Community
anwesham
commited on
Mar 11, 2022
Commit
ac07872
·
1 Parent(s):
0c2e610
Create README.md
Browse files
Files changed (1)
hide
show
README.md
+1
-0
README.md
ADDED
Viewed
@@ -0,0 +1 @@
1
+
AI4Bharat\'s IndicBERT finetuned for few-shot transfer learning by fine-tuning on Hindi training data with Urdu validation and test sets. Expected low accuracy. Leverages mbert\'s tokenizer in this implementation.