Update README.md
Browse files
README.md
CHANGED
|
@@ -10,9 +10,10 @@ tokenizer = AlbertTokenizer.from_pretrained("prajdabre/IndicBARTTokenizer", do_l
|
|
| 10 |
|
| 11 |
# Or use tokenizer = AutoTokenizer.from_pretrained("prajdabre/IndicBARTTokenizer", do_lower_case=False, use_fast=False, keep_accents=True)
|
| 12 |
|
| 13 |
-
model =
|
|
|
|
|
|
|
| 14 |
|
| 15 |
-
# Or use model = MBartForConditionalGeneration.from_pretrained("prajdabre/IndicBART")
|
| 16 |
|
| 17 |
# 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>".
|
| 18 |
inp = tokenizer("I am a boy <\/s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
|
|
|
|
| 10 |
|
| 11 |
# Or use tokenizer = AutoTokenizer.from_pretrained("prajdabre/IndicBARTTokenizer", do_lower_case=False, use_fast=False, keep_accents=True)
|
| 12 |
|
| 13 |
+
model = MBartForConditionalGeneration.from_pretrained("prajdabre/IndicBART")
|
| 14 |
+
|
| 15 |
+
# Or use model = AutoModelForSeq2SeqLM.from_pretrained("prajdabre/IndicBART")
|
| 16 |
|
|
|
|
| 17 |
|
| 18 |
# 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>".
|
| 19 |
inp = tokenizer("I am a boy <\/s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
|