Update app.py

app.py

@@ -1,10 +1,14 @@
 import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-with gr.Blocks(fill_height=True) as demo:
-    with gr.Sidebar():
-        gr.Markdown("# Inference Provider")
-        gr.Markdown("This Space showcases the agentica-org/DeepScaleR-1.5B-Preview model, served by the hf-inference API. Sign in with your Hugging Face account to use this API.")
-        button = gr.LoginButton("Sign in")
-    gr.load("models/agentica-org/DeepScaleR-1.5B-Preview", accept_token=button, provider="hf-inference")
-    
-demo.launch()
+model_name = "agentica-org/DeepScaleR-1.5B-Preview"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+def generate_response(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_length=100)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+iface = gr.Interface(fn=generate_response, inputs="text", outputs="text", title="DeepScaleR Text Generator")
+iface.launch()