Update app.py

app.py

@@ -2,31 +2,23 @@ import gradio as gr
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-# Use the smaller 1.5B model for stability
 model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
 
 print("Loading model...")
-
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-
 model = AutoModelForCausalLM.from_pretrained(
     model_name,
     device_map="auto"
 )
-
 print("Model loaded!")
 
 def chat(message, history):
     try:
         conversation = ""
-
-        # Keep last 3 messages to avoid overload
         for user, bot in history[-3:]:
             conversation += f"User: {user}\nAssistant: {bot}\n"
-
         conversation += f"User: {message}\nAssistant:"
 
-        # Tokenize with truncation
         inputs = tokenizer(
             conversation,
             return_tensors="pt",
@@ -44,20 +36,16 @@ def chat(message, history):
         )
 
         response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-
-        # Keep only latest assistant response
         response = response.split("Assistant:")[-1].strip()
-
         return response
 
     except Exception as e:
-        return f"⚠️ Error: Model overloaded. Try again with a shorter question."
+        return f"Error: {str(e)}"
 
-# Gradio chat interface
 iface = gr.ChatInterface(
     fn=chat,
-    title="Emalawi19 AI 🤖",
-    description="Chat with your own AI assistant powered by DeepSeek"
+    title="DeepSeek Chat AI",
+    description="Chat with DeepSeek 1.5B model"
 )
 
 iface.launch()