Update README.md

README.md

@@ -6,19 +6,24 @@ Usage:
 from transformers import MBartForConditionalGeneration, AutoModelForSeq2SeqLM
 from transformers import AlbertTokenizer, AutoTokenizer
 
-tokenizer = AlbertTokenizer.from_pretrained("prajdabre/IndicBARTTokenizer", do_lower_case=False, use_fast=False, keep_accents=True)
+tokenizer = AutoTokenizer.from_pretrained("prajdabre/IndicBARTTokenizer", do_lower_case=False, use_fast=False, keep_accents=True)
 
-# Or use tokenizer = AutoTokenizer.from_pretrained("prajdabre/IndicBARTTokenizer", do_lower_case=False, use_fast=False, keep_accents=True)
+# Or use tokenizer = AlbertTokenizer.from_pretrained("prajdabre/IndicBARTTokenizer", do_lower_case=False, use_fast=False, keep_accents=True)
 
-model = MBartForConditionalGeneration.from_pretrained("prajdabre/IndicBART")
+model = AutoModelForSeq2SeqLM.from_pretrained("prajdabre/IndicBART")
 
-# Or use model = AutoModelForSeq2SeqLM.from_pretrained("prajdabre/IndicBART")
+# Or use model = MBartForConditionalGeneration.from_pretrained("prajdabre/IndicBART")
 
+# Some initial mapping
+bos_id = tokenizer._convert_token_to_id_with_added_voc("<s>")
+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>". 
-inp = tokenizer("I am a boy <\/s> <2en>", 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 # 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
+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]])
 
 model_outputs=model(input_ids=inp, decoder_input_ids=out[:,0:-1], labels=out[:,1:])
 
@@ -32,7 +37,7 @@ model_outputs.logits
 
 model.eval() # Det dropouts to zero
 
-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])
+model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=20, min_length=1, early_stopping=True, pad_token_id=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
 
 
 # Decode to get output strings
@@ -45,7 +50,7 @@ print(decoded_output) # I am a boy
 
 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, decoder_start_token_id=tokenizer(["<2en>"], 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=pad_id, bos_token_id=bos_id, eos_token_id=eos_id, decoder_start_token_id=tokenizer._convert_token_to_id_with_added_voc("<2en>"))
 
 decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
 
@@ -54,6 +59,4 @@ print(decoded_output) # I am happy
 
 Notes:
 1. This is compatible with the latest version of transformers but was developed with version 4.3.2 so consider using 4.3.2 if possible.
-2. The tokenizer repo is kept separate from the model repo because unlike mBART-25 and mBART-50 which use a BPE model (MBartTokenizer class) whereas we use the sentencepiece model (AlbertTokenizer class).
-3. Currently, keeping the tokenizer and model files in the same repo complicates things so keeping them separate is a temporary solution. This will be fixed in future versions.
-4. While I have only shown how to let logits and loss and how to generate outputs, you can do pretty much everything the MBartForConditionalGeneration class can do as in https://huggingface.co/docs/transformers/model_doc/mbart#transformers.MBartForConditionalGeneration
+2. While I have only shown how to let logits and loss and how to generate outputs, you can do pretty much everything the MBartForConditionalGeneration class can do as in https://huggingface.co/docs/transformers/model_doc/mbart#transformers.MBartForConditionalGeneration