@echo off
Title 🦙 Llama.cpp Local Server - GPU + Model Selector + Auto Chrome

REM --- PATH SETTINGS ---
SET BASE_DIR=D:\Flie\llama.cpp
SET MODELS_DIR=%BASE_DIR%\models
SET SERVER_EXE=%BASE_DIR%\llama-server.exe

REM --- SERVER SETTINGS ---
SET HOST_IP=0.0.0.0
SET PORT=8080
SET GPU_LAYERS=999
SET CONTEXT_SIZE=4096

echo ============================================
echo   🦙 Llama.cpp Local Server - Model Selector
echo ============================================
echo.
echo Available Models in: %MODELS_DIR%
echo.

REM --- LIST ALL MODELS ---
SETLOCAL ENABLEDELAYEDEXPANSION
SET COUNT=0
for %%f in ("%MODELS_DIR%\*.gguf") do (
    SET /A COUNT+=1
    echo !COUNT!. %%~nxf
    SET "MODEL[!COUNT!]=%%~nxf"
)

echo.
set /p choice=Enter the model number to load: 

IF "%choice%"=="" (
    echo No selection made. Exiting...
    pause
    exit /b
)

SET SELECTED_MODEL=!MODEL[%choice%]!
echo.
echo ✅ Selected model: %SELECTED_MODEL%
echo ---------------------------------------------

SET MODEL_PATH="%MODELS_DIR%\%SELECTED_MODEL%"

echo Starting llama-server with %SELECTED_MODEL% on GPU...
echo.

REM --- START SERVER ---
start "" "%SERVER_EXE%" --n-gpu-layers %GPU_LAYERS% --ctx-size %CONTEXT_SIZE% --port %PORT% --host %HOST_IP% -m %MODEL_PATH%

REM --- OPEN CHROME AUTOMATICALLY ---
timeout /t 2 >nul
start "" chrome http://127.0.0.1:%PORT%/

echo.
echo 🦙 Server started. Browser should open automatically.
pause