Update README.md

README.md

@@ -6,56 +6,33 @@ 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("prajdabre/CreoleM2M", 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("prajdabre/CreoleM2M", do_lower_case=False, use_fast=False, keep_accents=True)
 
-model = AutoModelForSeq2SeqLM.from_pretrained("prajdabre/IndicBART")
+model = AutoModelForSeq2SeqLM.from_pretrained("prajdabre/CreoleM2M")
 
-# Or use model = MBartForConditionalGeneration.from_pretrained("prajdabre/IndicBART")
+# Or use model = MBartForConditionalGeneration.from_pretrained("prajdabre/CreoleM2M")
 
 # 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>']
+# To get lang_id use any of ["<s>", "</s>", "<2acf>", "<2eng>", "<2bis>", "<2bzj>", "<2cbk>", "<2crs>", "<2djk>", "<2gul>", "<2hat>", "<2hwc>", "<2icr>", "<2jam>", "<2kri>", "<2ktu>", "<2mbf>", "<2mfe>", "<2mkn>", "<2pap>", "<2pcm>", "<2pis>", "<2rop>", "<2sag>", "<2srm>", "<2srn>", "<2tcs>", "<2tdt>", "<2tpi>"]
 
-# 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 # 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]])
-
-model_outputs=model(input_ids=inp, decoder_input_ids=out[:,0:-1], labels=out[:,1:])
-
-# For loss
-model_outputs.loss ## This is not label smoothed.
-
-# For logits
-model_outputs.logits
-
-# For generation. Pardon the messiness. Note the decoder_start_token_id.
+# First tokenize the input and outputs. The format below is how CreoleM2M was trained so the input should be "Sentence </s> <2xxx>" where xxx is the language code. Similarly, the output should be "<2yyy> Sentence </s>". 
+inp = tokenizer('Wen dey wen stretch him out fo whip him real hard , Paul wen tell da captain dat stay dea , “ Dis okay in da rules fo da Rome peopo ? fo you fo whip one guy dat get da same rights jalike da Rome peopo ? even one guy dat neva do notting wrong ? ' </s> <2hwc>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
 
 model.eval() # Set 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=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>"))
+model_output=model.generate(inp, use_cache=True, num_beams=4, max_length=60, 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("<eng>"))
 
 
 # Decode to get output strings
 
 decoded_output=tokenizer.decode(model_output[0], skip_special_tokens=True, clean_up_tokenization_spaces=False)
 
-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=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)
-
-print(decoded_output) # I am happy
-```
+print(decoded_output)
 
 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.