Update README.md

README.md

@@ -22,7 +22,24 @@ This is a narrow domain-expert LLM trained on the top 5 books on Gutenberg:
 - The Prince (Machiavelli)
 - Second Treatise of Government
 
-It's meant to be an interesting novelty, showing off training on a specific domain. I also forgot to include any generalist assistant data so it's not likely to be good at much else besides answering philosophy questions.
+It's meant to be an interesting novelty, showing off training on a specific domain. It has some quirks. Namely:
+
+1. It seems to have memorized the training data very well. Ask a question that exists in the training data, with temp 0, and it will usually give you back the exact response word-for-word. This means that, on the subjects covered by its data, it will be very knowledgeable.
+2. I forgot to include any generalist instruct data, so it's... not stupid, at least not particularly stupid by 7b standards, but it is very much limited to QA.
+3. It's much less fluffy and wasteful with its responses than previous Augmentoolkit domain expert models, due to using a new dataset setting. This tends to make it respond with less detail, but it also may remember stuff better and get to the point easier.
+
+Some example chats (blame LM studio for not hiding the stop token):
+
+Asking stuff from the training data:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64825ebceb4befee377cf8ac/AirHFo61iB1HAP-IXwnZn.png)
+
+Asking a question directly from the training data and
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64825ebceb4befee377cf8ac/Ccm-EeDyOFcylCefwDS-W.png)
+
+Some things that are kinda funny but also show off the drawback of not using any generalist data:
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64825ebceb4befee377cf8ac/e2sCBLIX8Xg91KSevGt_B.png))
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64825ebceb4befee377cf8ac/P0bhWyENxOaxPvC4fE6jw.png)
 
 ## Training procedure