Update README.md

README.md

@@ -30,7 +30,7 @@ pip install causal-conv1d>=1.2.0
 pip install mamba-ssm
 ```
 
-If any of these two is not installed, the "eager" implementation will be used(not recommended). Otherwise the more optimised `cuda` kernels will be used.
+If any of these two is not installed, the "eager" implementation will be used(not recommended). Otherwise the more optimised `CUDA` kernels will be used.
 
 ### Generation
 
@@ -76,7 +76,7 @@ print(tokenizer.batch_decode(out))
 
 ### On-device Inference
 
-Since Mambaoutai is only 1.6B parameters, it can run on a CPU at a a fast speed.
+Since Mambaoutai is only 1.6B parameters, it can be run on a CPU with reasonable speed.
 
 Here is an example of how to run it on llama.cpp: