Update README.md

README.md

@@ -1,4 +1,4 @@
-This is the IndicBART model. For detailed documentation look here: https://indicnlp.ai4bharat.org/indic-bart/ and https://github.com/AI4Bharat/indic-bart/
+This is the IndicBARTSS model. For detailed documentation look here: https://indicnlp.ai4bharat.org/indic-bart/ and https://github.com/AI4Bharat/indic-bart/
 
 Usage:
 
@@ -6,13 +6,13 @@ Usage:
 from transformers import MBartForConditionalGeneration, AutoModelForSeq2SeqLM
 from transformers import AlbertTokenizer, AutoTokenizer
 
-tokenizer = AutoTokenizer.from_pretrained("prajdabre/IndicBART", do_lower_case=False, use_fast=False, keep_accents=True)
+tokenizer = AutoTokenizer.from_pretrained("ai4bharat/IndicBARTSS", do_lower_case=False, use_fast=False, keep_accents=True)
 
-# Or use tokenizer = AlbertTokenizer.from_pretrained("prajdabre/IndicBART", do_lower_case=False, use_fast=False, keep_accents=True)
+# Or use tokenizer = AlbertTokenizer.from_pretrained("ai4bharat/IndicBARTSS", do_lower_case=False, use_fast=False, keep_accents=True)
 
-model = AutoModelForSeq2SeqLM.from_pretrained("prajdabre/IndicBART")
+model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/IndicBARTSS")
 
-# Or use model = MBartForConditionalGeneration.from_pretrained("prajdabre/IndicBART")
+# Or use model = MBartForConditionalGeneration.from_pretrained("ai4bharat/IndicBARTSS")
 
 # Some initial mapping
 bos_id = tokenizer._convert_token_to_id_with_added_voc("<s>")
@@ -20,7 +20,7 @@ eos_id = tokenizer._convert_token_to_id_with_added_voc("</s>")
 pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>")
 # To get lang_id use any of ['<2as>', '<2bn>', '<2en>', '<2gu>', '<2hi>', '<2kn>', '<2ml>', '<2mr>', '<2or>', '<2pa>', '<2ta>', '<2te>']
 
-# First tokenize the input and outputs. The format below is how IndicBART was trained so the input should be "Sentence </s> <2xx>" where xx is the language code. Similarly, the output should be "<2yy> Sentence </s>". 
+# First tokenize the input and outputs. The format below is how IndicBARTSS was trained so the input should be "Sentence </s> <2xx>" where xx is the language code. Similarly, the output should be "<2yy> Sentence </s>". 
 inp = tokenizer("I am a boy </s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids # tensor([[  466,  1981,    80, 25573, 64001, 64004]])
 
 out = tokenizer("<2hi> मैं  एक लड़का हूँ </s>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids # tensor([[64006,   942,    43, 32720,  8384, 64001]])