Update app.py

app.py

@@ -1,24 +1,23 @@
 import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
-model_name = "google/gemma-2b-it"
+model_name = "mistralai/Mistral-7B-Instruct-v0.1"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
 
 pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 def chat(user_input, history=[]):
-    prompt = f"<start_of_turn>user\n{user_input}<end_of_turn>\n<start_of_turn>model\n"
+    prompt = f"[INST] {user_input} [/INST]"
     result = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7)
-    response = result[0]["generated_text"].split("<start_of_turn>model\n")[-1].strip()
+    response = result[0]["generated_text"].replace(prompt, "").strip()
     history.append((user_input, response))
     return history, history
 
 gr.ChatInterface(
     fn=chat,
-    title="🤖 Mobe 2.0 - Your Personal AI",
-    description="Welcome to Mobe 2.0 – Powered by Gemma 2B | Developed by Ronobir",
-    theme="soft",
-    examples=["তুমি কে?", "Python দিয়ে কিভাবে ফাংশন বানায়?", "AI কীভাবে কাজ করে?"]
+    title="🤖 Mobe 2.0 - Personal AI by Ronobir",
+    description="Powered by Mistral 7B | 100% Free",
+    theme="soft"
 ).launch()