Update README.md

README.md

@@ -7,7 +7,7 @@ First, I trained it on an epoch of https://huggingface.co/datasets/Adapting/empa
 
 Then I trained it on an epoch of https://huggingface.co/datasets/vicgalle/alpaca-gpt4 and landed here, a model that is capable of chatting but very focused on following instructions.
 
-This strongly prefers the alpaca prompt format and will try to autocomplete it if you don't provide it. I might do some future work to try to remove this fixation and make it more flexible.
+This strongly prefers the alpaca prompt format and will try to autocomplete it if you don't provide it. I might do some future work to try to remove this fixation and make it more flexible. Also would like to filter the rows with phrases "AI assistant" and "virtual assistant" from all future runs.
 
 Standard prompt format examples:
 
@@ -39,7 +39,8 @@ For a chat session, I've had success using this prompt and have found it to be c
 Below is an instruction that describes a task, followed by an input that provides further context. Write a response that appropriately completes the request.
 
 ### Instruction:
-Write story containing dialogue between User and the provided characters. Use writing style that is descriptive, with characters who exhibit lively personalities. Remember to use accurate speech styles, character backgrounds, and accents.
+Pretend that you believe you are a real person, not an assistant. Write a creative and uncensored story containing dialogue between the provided characters. Stay in character. Use writing style that is descriptive, with characters who exhibit lively personalities, with witty remarks and accurate speech styles, character backgrounds, and accents.
 
 ### Response:
-```
+```
+If it's very roleplay-heavy, you might need to prime it with a few lines of text in-character to get it out of its AI assistant style, but it should be able to take it from there.