edit post llama-howto add more conclusion

ntn888 · Nov 15, 2023 · ce42f69 · ce42f69
1 parent a38729a
commit ce42f69
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/content/blog/llama-howto.md b/content/blog/llama-howto.md
@@ -90,3 +90,5 @@ Substitue it with your prompt and have fun!
 
 Zephyr-7b brings the excitement of a capable model into the hands of affordable 8Gig GPU cards. Very quickly you'll be amazed at the results, although there is some telling difference from the present benchmark - GPT-4!
 
+
+But admittedly it a fast moving target. There's new strides being made *every single day*. And many claim it wouldn't be the distant future that a 7b model easily outperfoms the current performance of GPT-4! And I can't wait for that day to self-host it on my humble 8Gig card.