Update README.md

README.md

@@ -12,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 Tried depth-upscaling Cosmo-1b by duplicating 6 layers, then LISA-training on a dataset reasonably similar to the original one in an attempt to 'self-repair'.
 
-Not sure if it worked out exactly how I pictured but the nous eval's not overall worse than the original at least.
+Not sure if it worked out exactly how I pictured but the nous eval's not overall much worse than the original at least.
 
 (Took I think about 8 hours for, I want to say, ~80 million tokens on one RTX 3090?)