fix: correct broken batch file paths and update README

- start-llama-server.bat: fix LLAMA_DIR to bin\llama (was bin\ollama),
  fix model to qwen2.5-coder-1.5b (was Llama-3.2-1B), use correct
  GPU (llama-server.exe) and CPU (cpu\llama-server-cpu.exe) binaries
- start-windows-mcp.bat: remove dead python313\ tier, use single
  embedded Python 3.13 at python\python.exe
- run-hermes.bat: use Scripts\hermes.exe instead of -m hermes_cli
  (no __main__.py in package), fix offline mode to use single
  config.yaml instead of non-existent config.offline.yaml
- run-hermes.ps1: same hermes_cli → hermes.exe fix
- README.txt: update to match actual USB state (Python 3.13, 142
  wheels, Qwen2.5-Coder-1.5B 1117MB model, correct dir structure)

build/output/start-llama-server.bat

@@ -22,9 +22,11 @@ cd /d "%~dp0"
 
 
 
-set LLAMA_DIR=%~dp0bin\ollama
+set LLAMA_DIR=%~dp0bin\llama
 
-set MODEL=%LLAMA_DIR%\Llama-3.2-1B-Instruct-Q4_K_M.gguf
+set OLLAMA_DIR=%~dp0bin\ollama
+
+set MODEL=%OLLAMA_DIR%\qwen2.5-coder-1.5b-q4_k_m.gguf
 
 set PORT=11434
 
@@ -172,7 +174,7 @@ if !GPU_FOUND! equ 1 (
 
     echo [*] Starting llama-server with GPU acceleration (Vulkan)...
 
-    echo [*] Model: Llama-3.2-1B (Q4_K_M)
+    echo [*] Model: Qwen2.5-Coder-1.5B (Q4_K_M)
 
     echo [*] Server: http://127.0.0.1:!PORT!/v1
 
@@ -186,7 +188,7 @@ if !GPU_FOUND! equ 1 (
 
 
 
-    "!LLAMA_DIR!\llama-server-vulkan.exe" ^
+    "!LLAMA_DIR!\llama-server.exe" ^
 
         --host 127.0.0.1 --port !PORT! ^
 
@@ -206,7 +208,7 @@ if !GPU_FOUND! equ 1 (
 
     echo [*] No compatible GPU found. Starting CPU-only mode.
 
-    echo [*] Model: Llama-3.2-1B (Q4_K_M)
+    echo [*] Model: Qwen2.5-Coder-1.5B (Q4_K_M)
 
     echo [*] Server: http://127.0.0.1:!PORT!/v1
 
@@ -220,7 +222,7 @@ if !GPU_FOUND! equ 1 (
 
 
 
-    "!LLAMA_DIR!\llama-server.exe" ^
+    "!LLAMA_DIR!\cpu\llama-server-cpu.exe" ^
 
         --host 127.0.0.1 --port !PORT! ^
 
@@ -241,4 +243,3 @@ echo.
 echo [*] Server exited with code !errorlevel!
 
 pause
-