load model correction

scripts/generate_scripts.py

@@ -9,15 +9,16 @@ import spaces
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "Qwen/Qwen2.5-0.5B"
 
-tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32, trust_remote_code=True).to(device)
 
 
 @spaces.GPU()
 def generate_local(prompt: str, max_new_tokens: int = 350, temperature: float = 0.7) -> str:
+    model_id = "Qwen/Qwen2.5-0.5B"
     device = torch.device("cuda" if torch.cuda.is_available() else "cpu")  # get the device the model is on
+
+    tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float32, trust_remote_code=True).to(device)
     inputs = tokenizer(prompt, return_tensors="pt").to(device)
     
     output_ids = model.generate(