Update README.md

README.md

@@ -3,20 +3,19 @@ widget:
 - text: "मुझे उनसे बात करना <mask> अच्छा लगा"
 - text: "हम आपके सुखद <mask> की कामना करते हैं"
 - text: "सभी अच्छी चीजों का एक <mask> होता है"
+inference: false
 ---
 
 # RoBERTa base model for Hindi language
 
-Pretrained model on Hindi language using a masked language modeling (MLM) objective. RoBERTa was introduced in
-[this paper](https://arxiv.org/abs/1907.11692) and first released in
-[this repository](https://github.com/pytorch/fairseq/tree/master/examples/roberta).
+Pretrained model on Hindi language using a masked language modeling (MLM) objective. 
 
 > This is part of the
 [Flax/Jax Community Week](https://discuss.huggingface.co/t/pretrain-roberta-from-scratch-in-hindi/7091), organized by [HuggingFace](https://huggingface.co/) and TPU usage sponsored by Google.
 
 ## Model description
 
-RoBERTa Hindi is a transformers model pretrained on a large corpus of Hindi data in a self-supervised fashion.
+RoBERTa Hindi is a transformers model pretrained on a large corpus of Hindi data(a combination of **mc4, oscar and indic-nlp** datasets)
 
 ### How to use
 
@@ -55,7 +54,6 @@ The RoBERTa Hindi model was pretrained on the reunion of the following datasets:
 - [mC4](https://huggingface.co/datasets/mc4) is a multilingual colossal, cleaned version of Common Crawl's web crawl corpus.
 - [IndicGLUE](https://indicnlp.ai4bharat.org/indic-glue/) is a natural language understanding benchmark.
 - [Samanantar](https://indicnlp.ai4bharat.org/samanantar/) is a parallel corpora collection for Indic language.
-- [Hindi Wikipedia Articles - 172k](https://www.kaggle.com/disisbig/hindi-wikipedia-articles-172k) is a dataset with cleaned 172k Wikipedia articles.
 - [Hindi Text Short and Large Summarization Corpus](https://www.kaggle.com/disisbig/hindi-text-short-and-large-summarization-corpus) is a collection of ~180k articles with their headlines and summary collected from Hindi News Websites.
 - [Hindi Text Short Summarization Corpus](https://www.kaggle.com/disisbig/hindi-text-short-summarization-corpus) is a collection of ~330k articles with their headlines collected from Hindi News Websites.
 - [Old Newspapers Hindi](https://www.kaggle.com/crazydiv/oldnewspapershindi) is a cleaned subset of HC Corpora newspapers.
@@ -65,7 +63,7 @@ The RoBERTa Hindi model was pretrained on the reunion of the following datasets:
 
 The texts are tokenized using a byte version of Byte-Pair Encoding (BPE) and a vocabulary size of 50265. The inputs of
 the model take pieces of 512 contiguous token that may span over documents. The beginning of a new document is marked
-with `<s>` and the end of one by `</s>`
+with `<s>` and the end of one by `</s>`. We also did some preliminary cleanup of **mC4** and **oscar** datasets by removing all non hindi(non Devanagiri) characters from the datasets. The model was then trained on a randomized shuffle of all the datasets combined. 
 The details of the masking procedure for each sentence are the following:
 - 15% of the tokens are masked.
 - In 80% of the cases, the masked tokens are replaced by `<mask>`.
@@ -74,10 +72,7 @@ The details of the masking procedure for each sentence are the following:
 Contrary to BERT, the masking is done dynamically during pretraining (e.g., it changes at each epoch and is not fixed).
 
 ### Pretraining
-The model was trained on Google Cloud Engine TPUv3-8 machine (with 335 GB of RAM, 1000 GB of hard drive, 96 CPU cores) **8 v3 TPU cores** for 42K steps with a batch size of 128 and a sequence length of 128. The
-optimizer used is Adam with a learning rate of 6e-4, \\(\beta_{1} = 0.9\\), \\(\beta_{2} = 0.98\\) and
-\\(\epsilon = 1e-6\\), a weight decay of 0.01, learning rate warmup for 24,000 steps and linear decay of the learning
-rate after.
+The model was trained on Google Cloud Engine TPUv3-8 machine (with 335 GB of RAM, 1000 GB of hard drive, 96 CPU cores) **8 v3 TPU cores** for 42K steps with a batch size of 128 and a sequence length of 128.
 
 ## Evaluation Results
 
@@ -91,11 +86,12 @@ RoBERTa Hindi is evaluated on downstream tasks. The results are summarized below
 | IITP Movie Reviews      | Sentiment Analysis   | 60.97     | 52.26      | **70.65**                         | 49.35                 | **61.29**         |
 
 ## Team Members
-- Kartik Godawat ([dk-crazydiv](https://huggingface.co/dk-crazydiv))
 - Aman K ([amankhandelia](https://huggingface.co/amankhandelia))
 - Haswanth Aekula ([hassiahk](https://huggingface.co/hassiahk))
-- Rahul Dev ([mlkorra](https://huggingface.co/mlkorra))
+- Kartik Godawat ([dk-crazydiv](https://huggingface.co/dk-crazydiv))
 - Prateek Agrawal ([prateekagrawal](https://huggingface.co/prateekagrawal))
+- Rahul Dev ([mlkorra](https://huggingface.co/mlkorra))
+
 
 ## Credits
 Huge thanks to Huggingface 🤗 & Google Jax/Flax team for such a wonderful community week. Especially for providing such massive computing resource. Big thanks to [Suraj Patil](https://huggingface.co/valhalla) & [Patrick von Platen](https://huggingface.co/patrickvonplaten) for mentoring during the whole week.