Update README.md

README.md

@@ -5,6 +5,8 @@ license: cc-by-nc-4.0
 
 This model was created by taking [Libra19B](https://huggingface.co/Envoid/Libra19B) and then using the [frankenllama script](https://huggingface.co/chargoddard/llama2-22b) to perform a block diagonal merge with [Enterredaas 33B](https://huggingface.co/Aeala/Enterredaas-33b).
 
+Unfortunately due to the lack of GQA **it does not** fit on a single 24 Gigabyte GPU at 4096 context and thus all testing was done with only 55 layers offloaded to GPU via q4_K_M gguf format. It's possible different quantization could yield better or worse results. 
+
 ## Unnatural corpus:
 
 I then used the included autocorpus.py script to generate 20 megabytes of raw text samples using Libra19B