Update app.py

app.py

@@ -67,8 +67,11 @@ vectorstore = LangChainFAISS(
 print("✅ FAISS vectorstore ready.")
 
 # === 5. Load GPT-2 for Generation ===
-tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
-model = AutoModelForCausalLM.from_pretrained("gpt2").to("cuda" if torch.cuda.is_available() else "cpu")
+#tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+#model = AutoModelForCausalLM.from_pretrained("gpt2").to("cuda" if torch.cuda.is_available() else "cpu")
+
+tokenizer = AutoTokenizer.from_pretrained("tiiuae/Falcon3-7B-Instruct")
+model = AutoModelForCausalLM.from_pretrained("tiiuae/Falcon3-7B-Instruct")
 
 text_gen_pipeline = pipeline(
     "text-generation",
@@ -82,7 +85,7 @@ text_gen_pipeline = pipeline(
 )
 
 llm = HuggingFacePipeline(pipeline=text_gen_pipeline)
-print("✅ GPT-2 loaded.")
+#print("✅ GPT-2 loaded.")
 
 # === 6. Prompt Formatting and Answer Logic ===
 def truncate_context(context, max_length=1024):