Fix README header structure and update CLI args to use __help

README.md

@@ -26,23 +26,30 @@ A Rust tool that binary-searches for the optimal GPU layer count (-ngl) when run
 
 ## CLI arguments
 
-Run with --help for full list:
-
-- -c, --ctx <CTX>
-  - Context size (in 1024-byte units). Default: 32.
-
-- -t, --threads <THREADS>
-  - Threads to pass to llama-server. Default: 32.
-- --port <PORT>
-  - Port for llama-server. Default: 11434.
-- --host <HOST>
-  - Host to bind. Default: 0.0.0.0.
-- -b, --batch <BATCH>
-  - CPU offload batch size. Default: 512.
-- -u, --ubatch <UBATCH>
-  - GPU offload batch size. Default: 256.
-- -v, --verbose
-  - Print llama-server logs instead of discarding them.
+Run with `__help` for full list:
+
+```
+-c, --ctx <CTX>
+  Context size (in 1024-byte units). Default: 32.
+
+-t, --threads <THREADS>
+  Threads to pass to llama-server. Default: 32.
+
+--port <PORT>
+  Port for llama-server. Default: 11434.
+
+--host <HOST>
+  Host to bind. Default: 0.0.0.0.
+
+-b, --batch <BATCH>
+  CPU offload batch size. Default: 512.
+
+-u, --ubatch <UBATCH>
+  GPU offload batch size. Default: 256.
+
+-v, --verbose
+  Print llama-server logs instead of discarding them.
+```
 
 ## Model selection