Update README.md

README.md

@@ -49,6 +49,9 @@ We want the good ending, not the bad one.
 
 ## Metrics
 
+
+Meausing the gguf, there is a difference in perplexity
+
 ```sh
 perplexity -m lmstudio-community/Meta-Llama-3-8B-Instruct-Q6_K.gguf -b 32 -c 512 -f wiki.test.raw
 # Final estimate: PPL = 7.5588 +/- 0.05599
@@ -58,7 +61,15 @@ perplexity -m cognitivecomputations/dolphin-2.9-llama3-8b-q5_K_M.gguf -b 32 -c 5
 # Final estimate: PPL = 9.9277 +/- 0.08261
 ```
 
-So yes this model edit does increase the perplexity :(. Perhaps if we didn't edit so many layers it would be better. It seems better than fine tuning (in the case of early dolphin versions)
+Measuring it in the original huggingface format, the increase is much small 
+(as a %, the absolute values are not comparable with the ones above as there are differences in measurement)
+
+model	|	perplexity|
+|-|-|
+|base	|295.462970|
+|orthogonalized	|309.856348|
+
+So yes this model edit does increase the perplexity :(. But more investigation is needed.
 
 ---
 license: llama3