Update README.md

README.md

@@ -10,8 +10,9 @@ tokenizer = AlbertTokenizer.from_pretrained("prajdabre/IndicBARTTokenizer", do_l
 model = MBartForConditionalGeneration.from_pretrained("prajdabre/IndicBART")
 
 # 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>". 
-inp = tokenizer("I am a boy </s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
-out = tokenizer("<2hi> मैं  एक लड़का हूँ </s>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
+inp = tokenizer("I am a boy <\/s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
+
+out = tokenizer("<2hi> मैं  एक लड़का हूँ <\/s>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
 
 model_outputs=model(input_ids=inp, decoder_input_ids=out[:,0:-1], labels=out[:,1:])
 
@@ -23,7 +24,7 @@ model_outputs.logits
 
 # For generation. Pardon the messiness. Note the decoder_start_token_id.
 
-model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer(["</s>"], add_special_tokens=False).input_ids[0][0], decoder_start_token_id=tokenizer(["<2en>"], add_special_tokens=False).input_ids[0][0], bos_token_id=tokenizer(["<s>"], add_special_tokens=False).input_ids[0][0])
+model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=tokenizer.pad_token_id, decoder_start_token_id=tokenizer(["<2en>"], add_special_tokens=False).input_ids[0][0])
 
 
 # Decode to get output strings
@@ -34,7 +35,7 @@ print(decoded_output) # I am a boy
 # What if we mask?
 
 inp = tokenizer("I am [MASK] </s> <2en>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
-model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer(["</s>"], add_special_tokens=False).input_ids[0][0], decoder_start_token_id=tokenizer(["<2en>"], add_special_tokens=False).input_ids[0][0], bos_token_id=tokenizer(["<s>"], add_special_tokens=False).input_ids[0][0])
+model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=tokenizer.pad_token_id, decoder_start_token_id=tokenizer(["<2en>"], add_special_tokens=False).input_ids[0][0])
 decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
 print(decoded_output) # I am happy