Update README.md

README.md

@@ -197,13 +197,15 @@ Special note:
 
 It appears "DRY" / "XTC" samplers has been added to LLAMACPP and SILLYTAVERN. 
 
-It is available (Llamacpp) via "llama-server.exe". Likely this sampler will also become available "downstream" in applications that use LLAMACPP in due time.
+It is available (Llamacpp) via "server.exe / llama-server.exe". Likely this sampler will also become available "downstream" in applications that use LLAMACPP in due time.
 
 [ https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md ]
 
 Operating Systems:
 
-Most AI/LLM apps operate on Windows, Mac, and Linux.
+Most AI/LLM apps operate on Windows, Mac, and Linux. 
+
+Mobile devices (and O/S) are in many cases also supported.
 
 ---
 
@@ -574,6 +576,22 @@ A word change, rephrasing, punctation , even a comma, or semi-colon can drastica
 
 Likewise the size, and complexity of your prompt impacts generation too ; especially clarity and direction.
 
+Special note:
+
+Pre-prompts / system role are not discussed here. Many of the model repo cards (at my repo) have an optional pre-prompt you can use to aid generation (and can impact instruction following too).
+
+Some of my newer models repo cards use a limited form of this called a "prose control" (discussed and shown by example).
+
+Roughly a pre-prompt / system role is embedded during each prompt and can act as a guide and/or set of directives for processing the prompt and/or containing generation instructions.
+
+A prose control is a simplifed version of this, which preceeds the main prompt(s) - but the idea / effect is relatively the same.
+
+I strongly suggest you research these online, as they are a powerful addition to your generation toolbox.
+
+They are especially potent with newer model archs due to newer model types having stronger instruction following ablities AND increase context too.
+
+PRIMARY SAMPLERS:
+
 <B>temp  /  temperature</B>
 
 temperature (default: 0.8)