Update README.md

README.md

@@ -3,8 +3,41 @@ tags:
 - conversational
 - tagalog
 - filipino
+
+language:
 - tl 
 
 ---
 
-# Tagalog DialoGPT Medium
+# Tagalog DialoGPT
+
+A DialoGPT model fine-tuned on Tagalog conversational data scraped from the web. This model is an output of a research on BERT-based data augmentation for low resource languages. The base model used is DialoGPT-medium.
+
+#  Latest release: July 25, 2021
+* As of the moment, the model is only able to respond based on the history of 3 previous utterances before being limited. This is a result of the scarcity of Tagalog conversations in our dataset.
+
+
+# Usage
+
+```
+for step in range(2):
+    # encode the new user input, add the eos_token and return a tensor in Pytorch
+    new_user_input_ids = tokenizer.encode(input(">> User:") + tokenizer.eos_token, return_tensors='pt')
+
+    # append the new user input tokens to the chat history
+    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if step > 0 else new_user_input_ids
+
+    # we limit the generation to 512 tokens, each utterance in training had a maximum of 128 tokens
+    chat_history_ids = model.generate(
+        bot_input_ids, max_length=512,
+        pad_token_id=tokenizer.eos_token_id,
+        num_beams=5, 
+        no_repeat_ngram_size=3
+    )
+    
+    # pretty print last ouput tokens from bot
+    print("DialoGPT: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
+```
+
+# Dataset and Scripts
+To be released