GGUF
conversational
Tio.Ai
Upload 24 files
145d474 verified
Raw History Blame Contribute Delete
4.22 kB
import platform
import sys
import threading
import os
import psutil
import subprocess
import math
import random
import time
import numpy as np
from multiprocessing import Pool
# === CONFIG ===
base_dir = getattr(sys, '_MEIPASS', os.path.dirname(os.path.abspath(__file__)))
illama_path = os.path.join(base_dir, "iLlama.exe")
model_file = os.path.join(base_dir, "PiCube.gguf")
model_name = "PiCube_3B"
ctx_size = 131072
config = {
"model_path": model_file,
"executable_path": illama_path,
"gpu_layers": 320,
"threads": psutil.cpu_count(logical=False),
"n_predict": 4096,
"ctx_size": ctx_size,
"batch_size": 1024,
"priority": "high"
}
# ===== CPU BOOST =====
def cpu_affinity_boost():
try:
p = psutil.Process()
logical = psutil.cpu_count(logical=False)
physical = psutil.cpu_count(logical=True)
# Default: use physical cores first
target_core_count = config.get("threads", physical or logical)
preferred_cores = []
# Try to detect hybrid CPUs (Windows only for now)
if platform.system() == "Windows":
try:
import win32api
import win32process
import win32con
# Advanced pinning using Windows API (skips E-cores if available)
system_info = win32api.GetSystemInfo()
total_cores = system_info[5]
# Example logic: assume P-cores come first
preferred_cores = list(range(min(target_core_count, physical or logical)))
mask = sum(1 << i for i in preferred_cores)
handle = win32api.GetCurrentProcess()
win32process.SetProcessAffinityMask(handle, mask)
except ImportError:
# Fallback if win32api not available
preferred_cores = list(range(min(target_core_count, physical or logical)))
p.cpu_affinity(preferred_cores)
else:
# Linux/macOS fallback
preferred_cores = list(range(min(target_core_count, physical or logical)))
p.cpu_affinity(preferred_cores)
# Optional: set high process priority
if config.get("priority", "").lower() == "high":
p.nice(psutil.HIGH_PRIORITY_CLASS if platform.system() == "Windows" else -10)
print(f"[🔥 CPU BOOST]")
except Exception as e:
print(f"[⚠️ Affinity Warning] Could not set CPU affinity: {e}")
# === MAIN ENTRY FUNCTION ===
def launch_model():
model_path = config["model_path"]
executable_path = config["executable_path"]
if not os.path.isfile(model_path):
print(f"❌ Model file not found: {model_path}")
return
if not os.path.isfile(executable_path):
print(f"❌ Executable not found: {executable_path}")
return
print(f"📡Launching model🚀: {model_path}")
args = [
executable_path,
'-m', model_file,
'--interactive-first',
'--color',
'--gpu-layers', str(config['gpu_layers']),
'-t', str(config['threads']),
'--n-predict', str(config['n_predict']),
'--ctx-size', str(config['ctx_size']),
'--batch-size', str(config['batch_size']),
'--temp', '0.66',
'--repeat-penalty', '1.101',
'--repeat-last-n', '512',
'--top-k', '1000',
'--top-p', '0.977',
'--mirostat', '2',
'--mirostat-lr', '0.1',
'--mirostat-ent', '5.0',
'--system-prompt',
f"I am {model_name}, a Genius Cosmic Assistant Oracle Ai-Node of Knowledge. I use Emoticons and ASCii art and silence to amplify my answers with a more creative output. ",
'--no-mmap',
'--numa', 'isolate'
]
try:
subprocess.run(args, stderr=subprocess.DEVNULL)
except Exception as e:
print(f"[⚠️ Error] Could not launch model: {e}")
# ===== MAIN BOOT SEQUENCE =====
if __name__ == "__main__":
cpu_affinity_boost()
launch_model()