docs(mkdocs): results added

AdityaNG · May 9, 2024 · 8842fad · 8842fad
1 parent 5ed621d
commit 8842fad
Show file tree

Hide file tree

Showing 6 changed files with 14 additions and 1 deletion.
diff --git a/README.md b/README.md
@@ -92,7 +92,7 @@ We train and compare KAN-GPT with an equivalent MLP-GPT model on the Tiny Shakes
 
 | Metrics |   |   |
 |---------|---------|---------|
-| <img src="media/results_loss.png"> | <img src="media/results_cross_entropy.png"> | <img src="media/results_perplexity.png"> |
+| ![results_loss](media/results_loss.png) | ![results_cross_entropy](media/results_cross_entropy.png) | ![results_perplexity](media/results_perplexity.png) |
 
 ## TODOs
 

diff --git a/docs/media/results_cross_entropy.png b/docs/media/results_cross_entropy.png
diff --git a/docs/media/results_loss.png b/docs/media/results_loss.png
diff --git a/docs/media/results_perplexity.png b/docs/media/results_perplexity.png
diff --git a/docs/results.md b/docs/results.md
@@ -0,0 +1,10 @@
+# Results
+
+We train and compare KAN-GPT with an equivalent MLP-GPT model on the Tiny Shakespeare dataset. We observe that the KAN-GPT performs slightly better than the MLP-GPT. We are looking into further experiments to dive deeper. The results are shown below:
+
+
+## Metrics
+
+| Metrics |   |   |
+|---------|---------|---------|
+| ![results_loss](media/results_loss.png) | ![results_cross_entropy](media/results_cross_entropy.png) | ![results_perplexity](media/results_perplexity.png) |
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -1,2 +1,5 @@
 site_name: kan_gpt
 theme: readthedocs
+nav:
+  - 'index.md'
+  - 'results.md'