Update README.md

README.md

@@ -29,7 +29,7 @@ model-index:
 
 <p>Dedicated to Nev.</p>
 
-<p><b>Version notes for 0.2</b>: Basically, reprocessed the whole dataset again, due to a severe mistake in previously used pipeline, which left the data poisoned with a lot of non-unicode characters. Now, no more weird generation artifacts, and more stability. Major kudos to Cahvay for his work on fixing this critical issue.</p>
+<p><b>Version notes for 0.1</b>: Reprocessed dataset (via Cahvay), readjusted training config for 8xH100 SXM. Significant improvements in instruction following, long context understanding and overall coherence over v0.0.</p>
 
 <p>
   <p>Prompt format is ChatML.</p><br>
@@ -63,7 +63,7 @@ model-index:
   <h3>
      Training time and hardware:
   </h3>
-      <ul><li>7 hours on 8xH100 SXM, provided by <a href=https://featherless.ai/>FeatherlessAI</a></li></ul><br>
+      <ul><li>12 hours on 8xH100 SXM, provided by <a href=https://featherless.ai/>FeatherlessAI</a></li></ul><br>
 </p>
   <p>Model was created by Kearm, Auri and Cahvay.</p>
   <h4>Special thanks:</h4><ul>