Create app.py

app.py

@@ -0,0 +1,33 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import spaces
+
+
+MODEL_NAME = 'NousResearch/Genstruct-7B'
+
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda', load_in_8bit=True)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+@spaces.GPU
+def generate_text(title, content):
+    msg = [{
+        'title': title,
+        'content': content
+    }]
+    inputs = tokenizer.apply_chat_template(msg, return_tensors='pt').cuda()
+    output = tokenizer.decode(model.generate(inputs, max_new_tokens=512)[0]).split(tokenizer.eos_token)[0]
+    return output
+
+demo = gr.Interface(
+    fn=generate_text,
+    inputs=[
+        gr.Textbox(label="Title"),
+        gr.Textbox(label="Content", lines=5)
+    ],
+    outputs=gr.Textbox(label="Generated Output", lines=10),
+    title="Genstruct-7B Text Generation Demo",
+    description="Enter a title and content to generate text using the Genstruct-7B model."
+)
+
+if __name__ == "__main__":
+    demo.launch()