TheLustriVA

import openai
from colorama import Fore

openai.api_base = "https://openrouter.ai/api/v1"
openai.api_key = "" #use own openrouter api key

system = "Your name is Bob. You are an intelligent and useful assistant that helps the user solve problems."
messages = [{"role" : "system", "content" : system},]

models = {

TheLustriVA

1. in Python script, make sure include #!/path/to/venv/python in the first line
2. add a systemd service $ sudo systemctl edit --force --full name.service. In the editor complete at least these statments,

[Unit]
Description=Python Service
Wants=network.target
After=network.target

[Service]
ExecStartPre=/bin/sleep 10

TheLustriVA

import torch
import numpy as np
import k_diffusion as K

from PIL import Image
from torch import autocast
from einops import rearrange, repeat

def pil_img_to_torch(pil_img, half=False):
    image = np.array(pil_img).astype(np.float32) / 255.0

TheLustriVA

# I added all the imports by hand
import torch
from torchvision.datasets import ImageFolder
from torchvision import transforms,models
from torch import nn,optim

# For all functions including this one, I wrote the name and docstring, and sometimes also the param names
def finetune(folder, model):
    """fine tune pytorch model using images from folder and report results on validation set"""
    if not os.path.exists(folder): raise ValueError(f"{folder} does not exist")

TheLustriVA

{
    "timezones": [
        "Africa/Abidjan",
        "Africa/Accra",
        "Africa/Addis_Ababa",
        "Africa/Algiers",
        "Africa/Asmara",
        "Africa/Asmera",
        "Africa/Bamako",
        "Africa/Bangui",