Update app.py

app.py

@@ -1,28 +1,16 @@
 import gradio as gr
 import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, pipeline
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
 # Model ID
 model_id = "large-traversaal/Alif-1.0-8B-Instruct"
 
-# 4-bit quantization configuration
-quantization_config = BitsAndBytesConfig(
-    load_in_4bit=True,
-    bnb_4bit_compute_dtype=torch.float16,
-    bnb_4bit_use_double_quant=True,
-    bnb_4bit_quant_type="nf4"
-)
-
-# Load tokenizer and model in 4-bit
+# Load tokenizer and model (CPU-friendly)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(
-    model_id,
-    quantization_config=quantization_config,
-    device_map="auto"
-)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cpu")  # Changed to CPU
 
 # Create text generation pipeline
-chatbot = pipeline("text-generation", model=model, tokenizer=tokenizer, device_map="auto")
+chatbot = pipeline("text-generation", model=model, tokenizer=tokenizer, device="cpu")  # Ensuring CPU use
 
 # Function to generate responses
 def chat(message):
@@ -32,12 +20,9 @@ def chat(message):
 # Gradio UI
 with gr.Blocks() as demo:
     gr.Markdown("# 🤖 Alif Chatbot - Urdu Language AI Model")
-    with gr.Row():
-        user_input = gr.Textbox(label="User Input", placeholder="اپنا سوال یہاں لکھیں...")
-    with gr.Row():
-        submit_btn = gr.Button("Send")
-    with gr.Row():
-        bot_response = gr.Textbox(label="AI Response")
+    user_input = gr.Textbox(label="User Input", placeholder="اپنا سوال یہاں لکھیں...")
+    submit_btn = gr.Button("Send")
+    bot_response = gr.Textbox(label="AI Response")
 
     submit_btn.click(fn=chat, inputs=user_input, outputs=bot_response)