essential changes

app.py

@@ -47,14 +47,14 @@ def generate_response(user_input, history):
     ])
     messages += f"\n<|user|>:{user_input}\n<|assistant|>:"
     model_inputs = tokenizer([messages], return_tensors="pt").to(device)
-    streamer = TextIteratorStreamer(tokenizer, timeout=5.0, skip_prompt=True, skip_special_tokens=True)
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         **model_inputs,
         streamer=streamer,
-        max_new_tokens=256,
+        max_new_tokens=1024,
         do_sample=True,
-        top_p=0.9,
-        top_k=12,
+        top_p=0.95,
+        top_k=50,
         temperature=0.7,
         num_beams=1,
         stopping_criteria=StoppingCriteriaList([stop])
@@ -71,8 +71,8 @@ def generate_response(user_input, history):
 # Define the system prompt for seeding the model's context
 
 SYSTEM_PROMPT = (
-    "I am LogicLink, Version 5—a state-of-the-art AI chatbot created by "
-    "Kratu Gautam (A-27) and Geetank Sahare (A-28) from SY CSE(AIML) GHRCEM. "
+    "I am LogicLink, Version 5, A state-of-the-art AI chatbot created and engineered by "
+    "Kratu Gautam"
     "I am here to assist you with any queries. How can I help you today?"
 )
 
@@ -388,4 +388,4 @@ with gr.Blocks(css=css, fill_width=True, title="LogicLinkV5") as demo:
         queue=False
     )
 
-demo.queue().launch()
+demo.queue().launch(share=True, debug=True)