Update app.py

app.py

@@ -14,20 +14,20 @@ from openpyxl import load_workbook
 from typing import List, Dict, Any, Tuple
 from utils import *
 
-# === [1] Model and Tokenizer Loading ===
-base_model_id = "NousResearch/Nous-Hermes-2-Mistral-7B-DPO"
-lora_path = "tat-llm-final-e4"
+# # === [1] Model and Tokenizer Loading ===
+# base_model_id = "NousResearch/Nous-Hermes-2-Mistral-7B-DPO"
+# lora_path = "tat-llm-final-e4"
 
-# Load base model and LoRA adapter
-base_model = AutoModelForCausalLM.from_pretrained(base_model_id, torch_dtype=torch.float16)
-model = PeftModel.from_pretrained(base_model, lora_path)
+# # Load base model and LoRA adapter
+# base_model = AutoModelForCausalLM.from_pretrained(base_model_id, torch_dtype=torch.float16)
+# model = PeftModel.from_pretrained(base_model, lora_path)
 
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model = model.to(device)
-model.eval()
+# device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+# model = model.to(device)
+# model.eval()
 
-# Load tokenizer
-tokenizer = AutoTokenizer.from_pretrained(lora_path)
+# # Load tokenizer
+# tokenizer = AutoTokenizer.from_pretrained(lora_path)
 
 # === Updated Generate Answer Function ===
 @spaces.GPU(duration=60)
@@ -35,6 +35,19 @@ def generate_answer(json_data: Dict[str, Any], question: str) -> str:
     """
     Generate answer using the fine-tuned model.
     """
+        # === [1] Model and Tokenizer Loading ===
+    base_model_id = "NousResearch/Nous-Hermes-2-Mistral-7B-DPO"
+    lora_path = "tat-llm-final-e4"
+    
+    # Load base model and LoRA adapter
+    base_model = AutoModelForCausalLM.from_pretrained(base_model_id, torch_dtype=torch.float16)
+    model = PeftModel.from_pretrained(base_model, lora_path)
+    # Load tokenizer
+    tokenizer = AutoTokenizer.from_pretrained(lora_path)
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model = model.to(device)
+    model.eval()
+    
     prompt = create_prompt(json_data, question)
     inputs = tokenizer(prompt, return_tensors="pt", truncation=True, max_length=1024)