Merge pull request #7 from jasondavies/typos

Fix typos.

README.md

@@ -14,7 +14,7 @@ We hope the release of bitnet.cpp can inspire more 1-bit LLMs trained in large-s
 
 ## Demo
 
-A demo of bitnet.cpp runing a BitNet b1.58 3B model on Apple M2:
+A demo of bitnet.cpp running a BitNet b1.58 3B model on Apple M2:
 
 https://github.com/user-attachments/assets/7f46b736-edec-4828-b809-4be780a3e5b1
 

docs/codegen.md

@@ -8,7 +8,7 @@ We cutting weight into multiple compute blocks to best utilize hardware capabili
 ### Example
 bitnet_b1_58-large:
 
-- Make sure Mamtul kernels shapes \
+- Make sure Matmul kernels shapes \
 For example, bitnet_b1_58-large Matmul kernel shapes are:\
 [1536, 4096]\
 [1536, 1536]\