Update README.md

README.md

@@ -18,7 +18,7 @@ Built using the DARE TIES merge method, it combines pre-trained language models
 The model configuration emphasizes long sequence lengths, conversation datasets, and dense reasoning abilities. 
 
 ## Note:
-If you want good reasoning power from this model, please use FP16 and XTC sampling.
+If you want good reasoning power from this model, please use BF16 and XTC sampling.
 
 
 ### Configuration