Update README.md

README.md

@@ -1,3 +1,45 @@
 ---
 license: other
+language:
+- en
 ---
+The Llama 2 sequel to my original experiment with gradient merges using [the following script](https://github.com/Gryphe/BlockMerge_Gradient). Its three models ([Hermes](https://huggingface.co/NousResearch/Nous-Hermes-Llama2-13b), [Chronos](https://huggingface.co/elinas/chronos-13b-v2) and [Airoboros](https://huggingface.co/jondurbin/airoboros-l2-13b-gpt4-2.0)) are almost evenly divided over the layer structure this time. Airoboros was the "wildcard model" due to its superior ability to understand complex instructions.
+
+Quantized models are available from TheBloke: [GGML](https://huggingface.co/TheBloke/MythoLogic-13B-GGML) - [GPTQ](https://huggingface.co/TheBloke/MythoLogic-13B-GPTQ) (You're the best!)
+
+## Model details
+
+As always, the main objective was to create an all-round model with improved roleplaying capabilities. MythoLogic-L2 differs from its predecessor in that it focuses primarily on the understanding of instructions and personalities of complex character cards.
+
+Illustrated below are the gradients used for this L2 recipe;
+
+[](approximation.png)
+
+## Prompt Format
+
+This model primarily uses (and wast tested 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>:
+```
+
+---
+license: other
+---