Update README.md

README.md

@@ -4,4 +4,33 @@ language:
 - si
 metrics:
 - perplexity
----
+---
+
+### Overview
+
+This is a slightly smaller model trained on half of the [Fasttext](https://fasttext.cc/docs/en/crawl-vectors.html) dataset. Since Sinhala is classified as a low-resource language, there is a significant scarcity of pre-trained models available for it. This lack of resources creates a noticeable gap in the language's representation within the field of natural language processing (NLP). As a result, developing new models tailored for Sinhala presents a valuable opportunity. This model can act as foundational tools to enable further advancements in downstream tasks such as sentiment analysis, machine translation, named entity recognition, or question answering. 
+## Model Specification
+
+
+The model chosen for training is [Roberta](https://arxiv.org/abs/1907.11692) with the following specifications:
+ 1. vocab_size=52000
+ 2. max_position_embeddings=514
+ 3. num_attention_heads=12
+ 4. num_hidden_layers=6
+ 5. type_vocab_size=1
+Perplexity Value - 3.5
+
+## How to Use
+You can use this model directly with a pipeline for masked language modeling:
+
+```py
+from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline
+
+model = AutoModelWithLMHead.from_pretrained("ashen/AshenBERTo")
+tokenizer = AutoTokenizer.from_pretrained("ashen/AshenBERTo")
+
+fill_mask = pipeline('fill-mask', model=model, tokenizer=tokenizer)
+
+fill_mask("මම ගෙදර <mask>.")
+
+```