Update README.md

README.md

@@ -24,8 +24,17 @@ licenses:
 
 # MultiIndicWikiBioUnified
 
-This repository contains the [IndicBART](https://huggingface.co/ai4bharat/IndicBART) checkpoint finetuned on the 9 languages of [IndicWikiBio](https://huggingface.co/datasets/ai4bharat/IndicWikiBio) dataset. For finetuning details,
-see the [paper](https://arxiv.org/abs/2203.05437). 
+MultiIndicWikiBioUnified is a multilingual, sequence-to-sequence pre-trained model, a [IndicBART](https://huggingface.co/ai4bharat/IndicBART) checkpoint fine-tuned on the 9 languages of [IndicWikiBio](https://huggingface.co/datasets/ai4bharat/IndicWikiBio) dataset. For fine-tuning details,
+see the [paper](https://arxiv.org/abs/2203.05437). You can use MultiIndicWikiBio to build biography generation applications for Indian languages by fine-tuning the model with supervised training data. Some salient features of the MultiIndicWikiBio are:
+
+<ul>
+<li >Supported languages: Assamese, Bengali, Hindi, Oriya, Punjabi, Kannada, Malayalam, Tamil, and Telugu. Not all of these languages are supported by mBART50 and mT5. </li>
+<li >The model is much smaller than the mBART and mT5(-base) models, so less computationally expensive for fine-tuning and decoding. </li>
+<li> Fine-tuned on an Indic language corpora (34,653 examples). </li>
+<li> All languages have been represented in Devanagari script to encourage transfer learning among the related languages. </li>
+</ul>
+
+You can read more about MultiIndicWikiBioUnified in this <a href="https://arxiv.org/abs/2203.05437">paper</a>.
 
 
 ## Using this model in `transformers`
@@ -33,38 +42,43 @@ see the [paper](https://arxiv.org/abs/2203.05437).
 ```
 from transformers import MBartForConditionalGeneration, AutoModelForSeq2SeqLM
 from transformers import AlbertTokenizer, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration", do_lower_case=False, use_fast=False, keep_accents=True)
-# Or use tokenizer = AlbertTokenizer.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration", do_lower_case=False, use_fast=False, keep_accents=True)
-model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration")
-# Or use model = MBartForConditionalGeneration.from_pretrained("ai4bharat/MultiIndicParaphraseGeneration")
+
+tokenizer = AutoTokenizer.from_pretrained("ai4bharat/MultiIndicWikiBioUnified", do_lower_case=False, use_fast=False, keep_accents=True)
+# Or use tokenizer = AlbertTokenizer.from_pretrained("ai4bharat/MultiIndicWikiBioUnified", do_lower_case=False, use_fast=False, keep_accents=True)
+
+model = AutoModelForSeq2SeqLM.from_pretrained("ai4bharat/MultiIndicWikiBioUnified")
+# Or use model = MBartForConditionalGeneration.from_pretrained("ai4bharat/MultiIndicWikiBioUnified")
+
 # 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 ['<2as>', '<2bn>', '<2hi>', '<2kn>', '<2ml>', '<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 # tensor([[  466,  1981,    80, 25573, 64001, 64004]])
+inp = tokenizer("<TAG> name </TAG> भीखा लाल <TAG> office </TAG> विधायक - 318 - हसनगंज विधान सभा निर्वाचन क्षेत्र , उत्तर प्रदेश <TAG> term </TAG> 1957 से 1962 <TAG> nationality </TAG> भारतीय</s><2hi>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids 
+
+out = tokenizer("<2hi> भीखा लाल ,भारत के उत्तर प्रदेश की दूसरी विधानसभा सभा में विधायक रहे। </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:])
+
+# 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.
 model.eval() # Set dropouts to zero
-model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, 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,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, 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("<2hi>"))
+
 # 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
-# Note that if your output language is not Hindi or Marathi, you should convert its script from Devanagari to the desired language using the Indic NLP Library.
-# 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,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, 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
-inp = tokenizer("मैं [MASK] हूँ </s> <2hi>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
-model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, 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) # मैं जानता हूँ
-inp = tokenizer("मला [MASK] पाहिजे </s> <2mr>", add_special_tokens=False, return_tensors="pt", padding=True).input_ids
-model_output=model.generate(inp, use_cache=True,no_repeat_ngram_size=3,encoder_no_repeat_ngram_size=3, 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) # मला ओळखलं पाहिजे
+
+print(decoded_output) # भीखा लाल ,भारत के उत्तर प्रदेश की दूसरी विधानसभा सभा में विधायक रहे।
+
+# Disclaimer
+Note that if your output language is not Hindi or Marathi, you should convert its script from Devanagari to the desired language using the [Indic NLP Library](https://github.com/AI4Bharat/indic-bart/blob/main/indic_scriptmap.py).
 ```
 # Note:
 If you wish to use any language written in a non-Devanagari script, then you should first convert it to Devanagari using the <a href="https://github.com/anoopkunchukuttan/indic_nlp_library">Indic NLP Library</a>. After you get the output, you should convert it back into the original script.