Update README.md

README.md

@@ -1,3 +1,23 @@
 ---
 license: other
+tags:
+- llama
+- llama-2
 ---
+               [Experimental model]
+
+This model is an experiment using the frankenstein script from 
+https://huggingface.co/chargoddard/llama2-22b
+BLOCK_DIAGONAL = False
+
+Using:
+https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16
+                          +
+Then used https://huggingface.co/upstage/llama-30b-instruct-2048
+as donor model.
+
+It used 160GB of system ram to merge these models, they merge fast without swap.
+
+For prompt template and model information see [huginnV1](https://huggingface.co/The-Face-Of-Goonery/Huginn-13b-FP16).
+
+This is probably my most coherent 22b model, this 22B model can still output spelling errors though.