Create app.py

app.py

@@ -0,0 +1,34 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import gradio as gr
+
+# Load model (cache on first run)
+model_id = "google/gemma-1.1-7b-it"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="auto",
+    torch_dtype=torch.bfloat16  # Optimized for NVIDIA
+)
+
+def generate_script(topic):
+    prompt = f"""Generate a viral YouTube Short script about {topic} with:
+    1) HOOK: Controversial opening (5 words max)
+    2) BODY: 3 scientific facts
+    3) CTA: Actionable challenge
+    
+    Script:"""
+    
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    outputs = model.generate(**inputs, max_new_tokens=300)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Gradio UI
+demo = gr.Interface(
+    fn=generate_script,
+    inputs=gr.Textbox(label="Topic"),
+    outputs=gr.Textbox(label="Generated Script"),
+    title="Gemma-7B Script Generator"
+)
+
+demo.launch(server_port=7860, share=True)