create README

README.md

@@ -1,3 +1,31 @@
 ---
 license: llama3
 ---
+
+# Llama-3-8B-Instruct-Gadsby
+
+![The letter E discarded in a dumpster.](img/discarded_e.webp)
+
+Introducing Llama 3 Instruct Gatsby, a modification to the Llama 3 instruct model that may lie, cheat, and deny the existence of elephants; but no matter what, it will not use the letter “E.”
+
+![A meme of an elephant hiding in the bushes.](img/elephant_hiding.webp)
+
+This generator of lipograms works through a very simple modification to the final layer of the Llama 3 model, zeroing out the weights corresponding to any tokens that would contain any variants of the letter "E."
+
+Example outputs below were generated using at the Q6_K quantization, but I've also included a few other quants to fit other use cases. The process to mask out a model in this way is very easy and can be done to other models.
+
+![Example output - Sushi Poem](img/e_free_sushi.webp)
+
+![Example output - Elephant Denial](img/cant_say_elephant.webp)
+
+![Example output - Woodchuck deconstruction](img/woodchuck_without_e.webp)
+
+![Example output - Can't say slumber or sleep](img/a_good_nights_slum.webp)
+
+For details on how to do this yourself, I have some example code in my medium post.
+
+https://medium.com/@coreyhanson/a-simple-way-to-program-an-llm-lipogram-83e84db41342
+
+In case there are any paywall shenanigans, I have also mirrored a copy on my website too.
+
+https://coreyhanson.com/blog/a-simple-way-to-program-an-llm-lipogram/