prajdabre commited on
Commit
6b7c5b4
1 Parent(s): 8875a3f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -1,4 +1,4 @@
1
- This is the IndicBART model. For detailed documentation look here: https://indicnlp.ai4bharat.org/indic-bart/ and https://github.com/AI4Bharat/indic-bart/
2
 
3
  Usage:
4
 
@@ -6,13 +6,13 @@ Usage:
6
  from transformers import MBartForConditionalGeneration, AutoModelForSeq2SeqLM
7
  from transformers import AlbertTokenizer, AutoTokenizer
8
 
9
- tokenizer = AutoTokenizer.from_pretrained("prajdabre/IndicBART", do_lower_case=False, use_fast=False, keep_accents=True)
10
 
11
- # Or use tokenizer = AlbertTokenizer.from_pretrained("prajdabre/IndicBART", do_lower_case=False, use_fast=False, keep_accents=True)
12
 
13
- model = AutoModelForSeq2SeqLM.from_pretrained("prajdabre/IndicBART")
14
 
15
- # Or use model = MBartForConditionalGeneration.from_pretrained("prajdabre/IndicBART")
16
 
17
  # Some initial mapping
18
  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>")
20
  pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>")
21
  # To get lang_id use any of ['<2as>', '<2bn>', '<2en>', '<2gu>', '<2hi>', '<2kn>', '<2ml>', '<2mr>', '<2or>', '<2pa>', '<2ta>', '<2te>']
22
 
23
- # 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>".
24
  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]])
25
 
26
  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]])
 
1
+ This is the IndicBARTSS model. For detailed documentation look here: https://indicnlp.ai4bharat.org/indic-bart/ and https://github.com/AI4Bharat/indic-bart/
2
 
3
  Usage:
4
 
 
6
  from transformers import MBartForConditionalGeneration, AutoModelForSeq2SeqLM
7
  from transformers import AlbertTokenizer, AutoTokenizer
8
 
9
+ tokenizer = AutoTokenizer.from_pretrained("ai4bharat/IndicBARTSS", do_lower_case=False, use_fast=False, keep_accents=True)
10
 
11
+ # Or use tokenizer = AlbertTokenizer.from_pretrained("ai4bharat/IndicBARTSS", do_lower_case=False, use_fast=False, keep_accents=True)
12
 
13
+ model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/IndicBARTSS")
14
 
15
+ # Or use model = MBartForConditionalGeneration.from_pretrained("ai4bharat/IndicBARTSS")
16
 
17
  # Some initial mapping
18
  bos_id = tokenizer._convert_token_to_id_with_added_voc("<s>")
 
20
  pad_id = tokenizer._convert_token_to_id_with_added_voc("<pad>")
21
  # To get lang_id use any of ['<2as>', '<2bn>', '<2en>', '<2gu>', '<2hi>', '<2kn>', '<2ml>', '<2mr>', '<2or>', '<2pa>', '<2ta>', '<2te>']
22
 
23
+ # 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>".
24
  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]])
25
 
26
  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]])