Create app.py

app.py

@@ -0,0 +1,34 @@
+# app.py
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Hugging Face model repo
+MODEL_REPO = "DSDUDEd/firebase"
+
+# Load tokenizer and model
+tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO)
+model = AutoModelForCausalLM.from_pretrained(MODEL_REPO)
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+def generate_response(prompt, max_tokens=100):
+    """Generate text from the model."""
+    inputs = tokenizer(prompt, return_tensors="pt").to(device)
+    outputs = model.generate(inputs["input_ids"], max_new_tokens=max_tokens)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+# Gradio interface
+iface = gr.Interface(
+    fn=generate_response,
+    inputs=[
+        gr.Textbox(label="Input Prompt"),
+        gr.Slider(minimum=10, maximum=500, step=10, label="Max Tokens")
+    ],
+    outputs=gr.Textbox(label="Model Output"),
+    title="Custom GPT-2 AI",
+    description="Type a prompt and the AI will generate a response."
+)
+
+if __name__ == "__main__":
+    iface.launch()