Update README.md

README.md

@@ -4,17 +4,27 @@ tags:
 - conversational
 license: mit
 ---
-An generative AI made using [microsoft/DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium).
+
+# Aeona | Chatbot
+![Aeona Banner](https://github.com/deepsarda/Aeona/blob/master/dashboard/static/banner.png?raw=true)
+
+
+
+An generative AI made using [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small).
+
+
+Recommended to use along with an [AIML Chatbot](https://github.com/deepsarda/Aeona-Aiml) to reduce load, get better replies, add name and personality to your bot.
+Using an AIML Chatbot will allow you to hardcode some replies also.
 
 # AEONA
 Aeona is an chatbot which hope's to be able to talk with humans as if its an friend!
 It's main target platform is discord. 
-You can invite the bot [here](https://aeona.repl.co/).
+You can invite the bot [here](https://aeona.xyz).
 
-To learn more about this project and chat with the ai, you can use this [website](https://aeona.repl.co/).
+To learn more about this project and chat with the ai, you can use this [website](https://aeona.xyx/).
 
 Aeona works why using context of the previous messages and guessing the personality of the human who is talking with it and adapting its own personality to better talk with the user.
-contact: [email protected]
+
 ## Goals
  The goal is to create an AI which will work with AIML in order to create the most human like AI.
  
@@ -29,15 +39,22 @@ contact: [email protected]
  3. Custom dataset scrapped from my messages, These messages are very narrow teaching this dataset and sending a random reply will make the AI say sorry loads of time!
     
 ## Training
-  The Discord Messages Dataset simply dwarfs the other datasets, Hence the data sets are repeated.
-  This leads to them covering each others issues!
+ The Discord Messages Dataset simply dwarfs the other datasets, Hence the data sets are repeated.
+ This leads to them covering each others issues!
   
+ The AI has a context of 6 messages which means it will reply until the 4th message from user.
+ [Example](https://huggingface.co/deepparag/Aeona-Beta/discussions/1)
+ 
+## Hugging Face interference, tips
+    I recommend send the user input,
+    previous 3 AI and human responses.
+    
+    Using more context than this will lead to useless responses but using less is alright but the responses may be random.  
 ## Evaluation 
-
 Below is a comparison of Aeona vs. other baselines on the mixed dataset given above using automatic evaluation metrics.
 
-| Model | Perplexity 
-|---|---|---
+| Model | Perplexity |
+|---|---|
 | Seq2seq Baseline [3] | 29.8 |
 | Wolf et al. [5] | 16.3 |
 | GPT-2 baseline | 99.5 |
@@ -47,6 +64,8 @@ Below is a comparison of Aeona vs. other baselines on the mixed dataset given ab
 | **Aeona** | **7.9** |
 
 ## Usage
+
+
 Example:
 ```python
 from transformers import AutoTokenizer, AutoModelWithLMHead
@@ -72,5 +91,5 @@ for step in range(4):
     )
     
     # pretty print last ouput tokens from bot
-    print("DumBot: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
+    print("Aeona: {}".format(tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)))
 ```