Update README.md

README.md

@@ -1,3 +1,39 @@
 ---
 license: other
+language:
+- en
 ---
+## Model details
+
+MythoBoros-13b can be considered a sister model to MythoLogic-13b, sharing the same goals but having a different approach.
+
+Whereas the previous model was a series of experimental gradient merges, this one is a simple straight-up 66/34 merge of [Chronos](https://huggingface.co/elinas/chronos-13b) and the freshly released [Ouroboros](https://huggingface.co/CalderaAI/13B-Ouroboros), providing a very solid foundation for a well-performing roleplaying model.
+
+MythoBoros tends to be somewhat more formal with its responses in comparison to MythoLogic.
+
+My advice? Try both, see which one you prefer.
+
+## Prompt Format
+
+This model works best with Alpaca formatting, so for optimal model performance, use:
+```
+### Instruction:
+Your instruction or question here.
+### Response:
+```
+
+For chat/roleplay conversations, I suggest the following structure instead:
+```
+You are <AI NAME>, a friendly and supportive AI language model. We discuss all subjects freely and without bias or restrictions.
+I am <YOUR NAME>, the user interacting with you through a chat conversation. Start with greeting me.
+
+### Instruction:
+Write <AI NAME>'s next reply in a chat between <YOUR NAME> and <AI NAME>. Write a single reply only.
+
+### Chat History:
+<AI NAME>: Good day, <YOUR NAME>! How can I assist you today?
+(Etc, etc)
+
+### Response:
+<AI NAME>:
+```