update

main.py

@@ -4,6 +4,7 @@ from fastapi.responses import FileResponse
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 import datetime
 import json
+import subprocess
 import torch
 
 def log(msg):
@@ -28,12 +29,18 @@ def get_prompt(user_query: str, functions: list = []) -> str:
 device : str = "cuda:0" if torch.cuda.is_available() else "cpu"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
+result = subprocess.run('ls -lh /.cache/huggingface/hub', shell=True, capture_output=True, text=True)
+log('Cache files: ' + result.stdout)
+
 model_id : str = "gorilla-llm/gorilla-openfunctions-v1"
 log('AutoTokenizer.from_pretrained ...')
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 log('AutoModelForCausalLM.from_pretrained ...')
 model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True)
 
+result = subprocess.run('ls -lh /.cache/huggingface/hub', shell=True, capture_output=True, text=True)
+log('Cache files: ' + result.stdout)
+
 log('mode.to(device) ...')
 model.to(device)