Update README.md

README.md

@@ -8,8 +8,13 @@ tags:
 ---
 # Llama-3.1-8B-InitializedEmbeddings_with_Hermes-3
 
+This is [Meta's LLaMA-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) (base model) pre-initialized to [NousResearch/Hermes-3-Llama-3.1-8B's](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) embedding's special tokens (prompt/chat template).
+
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
+Credit for the idea of this merge goes to Charles Goddard (Creator of mergekit); his merge [chargoddard/Meta-Llama-3-8B-InitializedEmbeds](https://huggingface.co/chargoddard/Meta-Llama-3-8B-InitializedEmbeds) outlined the details and explained how it all worked, and why it is necessary to pre-initialize the base model with the instruct model's embedding's special tokens.
+
+
 ## Merge Details
 ### Merge Method