dev

app.py

@@ -4,6 +4,7 @@ from llama_cpp import Llama
 from time import time
 import gradio as gr
 import psutil
+import os
 
 # load like this - use tne variable everywhere 
 model_path=os.getenv("MODEL_PATH")
@@ -30,11 +31,10 @@ print(f"DEBUG: Memory free: {psutil.virtual_memory().free / (1024.0 ** 3)} GiB")
 print(f"DEBUG: Memory available: {psutil.virtual_memory().available / (1024.0 ** 3)} GiB")
 print(f"DEBUG: Memory: {psutil.virtual_memory().total / (1024.0 ** 3)} GiB")
 
-import os
+
 from threading import Thread
 from typing import Iterator
 
-import gradio as gr
 import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer