Update app.py

app.py

@@ -97,10 +97,9 @@ def poem_to_image(poem):
 demo = gr.Blocks()
 
 with demo:
-  gr.Markdown("<h1><center>Generate Short Poem along with an Illustration</center></h1>")
+  gr.Markdown("<h1><center>Few Shot Learning for Text - Word Image Search</center></h1>")
   gr.Markdown(
-        "<div>Enter a single word you would want GPTJ-6B to write Poetry 🎤 on.</div>"
-        "<div>Generate an illustration 🎨 provided by Latent Diffusion model.</div><div>GPJ-6B is a 6 Billion parameter autoregressive language model. It generates the Poem based on how it has been 'prompt-engineered' 🤗 The complete text of generated poem then goes in as a prompt to the amazing Latent Diffusion Art space by <a href='https://huggingface.co/spaces/multimodalart/latentdiffusion' target='_blank'>Multimodalart</a>.</div>Please note that some of the Poems/Illustrations might not look at par, and well, this is what happens when you can't 'cherry-pick' and post 😁 <div> Some of the example words that you can use are 'river', 'night', 'trees', 'table', 'laughs' or maybe on similar lines to get best results!"
+        "<div>This example uses prompt engineering to search for answers in EleutherAI large language model and follows the pattern of Few Shot Learning where you supply A 1) Task Description, 2) a Set of Examples, and 3) a Prompt.  Then few shot learning can show the answer given the pattern of the examples. More information on how it works is here:  https://huggingface.co/blog/few-shot-learning-gpt-neo-and-inference-api  Also the Eleuther AI was trained on texts called The Pile which is documented here on its github.  Review this to find what types of language patterns it can generate text for as answers:  https://github.com/EleutherAI/the-pile"
     )
   with gr.Row():
     input_word = gr.Textbox(placeholder="Enter a word here to create a Poem on..")