Update README.md

README.md

@@ -7,9 +7,9 @@ Exllama quant of [Undi95/FlatDolphinMaid-8x7B](https://huggingface.co/Undi95/Fla
 
 You probably want this version. It just fits in 24gb of vram at half context (16384).
 
-If you really want the larger context [3.0](https://huggingface.co/Kooten/FlatDolphinMaid-8x7B-3bpw-exl2) should do it but you are probably better of with the gguf version with higher quants.
+If you really want the larger context [3bpw](https://huggingface.co/Kooten/FlatDolphinMaid-8x7B-3bpw-exl2) should do it but you are probably better of with the gguf version with higher quants.
 
-I did make a [4.0](https://huggingface.co/Kooten/FlatDolphinMaid-8x7B-4bpw-exl2), it might work in a headless or multigpu setup.
+I did make a [4bpw](https://huggingface.co/Kooten/FlatDolphinMaid-8x7B-4bpw-exl2), it might work in a headless or multigpu setup.