Update app.py

app.py

@@ -4,17 +4,13 @@ from peft import PeftModel
 import torch
 
 # --- Load tokenizer and model for CPU ---
-tokenizer = AutoTokenizer.from_pretrained("unsloth/Qwen3-1.7B")
-
-base_model = AutoModelForCausalLM.from_pretrained(
-    "unsloth/Qwen3-1.7B",
+tokenizer = AutoTokenizer.from_pretrained("khazarai/BioGenesis-ToT")
+model = AutoModelForCausalLM.from_pretrained(
+    "khazarai/BioGenesis-ToT",
     dtype=torch.float32,
     device_map={"": "cpu"},
 )
 
-model = PeftModel.from_pretrained(base_model, "khazarai/BioGenesis-ToT").to("cpu")
-
-
 # --- Chatbot logic ---
 def generate_response(user_input, chat_history):
     if not user_input.strip():