Update app.py

app.py

@@ -1,25 +1,27 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 
-# Load DeepSeek-R1 model
-model_name = "deepseek-ai/DeepSeek-R1"
+# ✅ Smaller DeepSeek model that runs on CPU
+model_name = "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B"
+
+# Load tokenizer & model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype="auto")
+
+# Create a text generation pipeline
+chatbot = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
-# Chat function
 def chat_with_ai(prompt):
-    inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(**inputs, max_new_tokens=250)
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
+    response = chatbot(prompt, max_new_tokens=200, do_sample=True, temperature=0.7)
+    return response[0]["generated_text"]
 
-# Gradio UI
+# Gradio interface
 ui = gr.Interface(
     fn=chat_with_ai,
-    inputs=gr.Textbox(label="Ask me anything..."),
+    inputs=gr.Textbox(label="Ask DeepSeek something..."),
     outputs="text",
-    title="💬 DeepSeek-R1 AI",
-    description="Chat with your own DeepSeek-R1 model hosted on Hugging Face Cloud!"
+    title="🤖 DeepSeek-R1 (Distilled Version)",
+    description="Chat with the smaller DeepSeek-R1 that runs even without a GPU!"
 )
 
 ui.launch()