modification to README

README.md

@@ -1,4 +1,5 @@
 ---
+thumbnail: https://huggingface.co/front/thumbnails/dialogpt.png
 language:
 - en
 license: cc-by-4.0
@@ -13,9 +14,44 @@ widget:
 - text: "I would like to have breakfast."
 ---
 
-DialoGPT_MWOZ
+## DialoGPT_MWOZ
 
 This is a fine-tuned model of DialoGPT (medium) on the MultiWOZ v2.2 dataset. It is intended to be used as a conversational system.
 The dataset it's trained on is limited in scope, as it covers only certain domains such as restaurants, hotel, taxi, train, hospital and police.
 
-The perplexity achieved on the test and validation sets are 10.25 and 10.71, respectively.
+The perplexity achieved on the test and validation sets are 10.25 and 10.71, respectively. More information about the original pre-trained model can be found [here](https://huggingface.co/microsoft/DialoGPT-medium)
+
+* Generation example from an interactive environment:
+
+|Role | Response |
+|---------|------------|
+|User | I would like to have breakfast. |
+|Bot | There are several options for Chinese in the city centre. Are you looking for a particular price range? |
+|User | I'm looking for free food |
+|Bot | There are 4 Chinese restaurants that are in the cheap price range. 3 in centre and one in north. |
+|User | Not good enough |
+|Bot | How about Charlie Chan? It is a Chinese restaurant in the centre of town. |
+
+Please find the information about preprocessing, training and full details of the DialoGPT in the [original DialoGPT repository](https://github.com/microsoft/DialoGPT)
+
+The paper for this work was accepted at the Northern Lights Deep Learning (NLDL) conference 2022. Arxiv paper: [https://arxiv.org/pdf/2110.06273.pdf](https://arxiv.org/pdf/2110.06273.pdf)
+
+### How to use
+
+Now we are ready to try out how the model works as a chatting partner!
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+tokenizer = AutoTokenizer.from_pretrained("tosin/dialogpt_mwoz")
+model = AutoModelForCausalLM.from_pretrained("tosin/dialogpt_mwoz")
+# Let's chat for 5 lines
+for step in range(5):
+	# 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
+	# generated a response while limiting the total chat history to 1000 tokens, 
+	chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+	# pretty print last ouput tokens from bot
+	print("DialoGPT_MWOZ_Bot: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))