add description

app.py

@@ -12,6 +12,12 @@ from mistral_common.protocol.instruct.request import ChatCompletionRequest
 from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
 import spaces
 
+title = "# **WIP / DEMO** 🙋🏻‍♂️Welcome to Tonic's Pixtral Image-to-Text Model Demo"
+description = """Upload an image to encode it. This is a **work in progress** , just showing off some demo features here until it's ready. 
+### Join us : 
+🌟TeamTonic🌟 is always making cool demos! Join our active builder's 🛠️community 👻 [![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/qdfnvSPcqP) On 🤗Huggingface:[MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to🌟 [Build Tonic](https://git.tonic-ai.com/contribute)🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗
+"""
+
 # Download model files
 model_path = snapshot_download(repo_id="mistral-community/pixtral-12b-240910")
 
@@ -104,8 +110,6 @@ def load_model(params, model_path):
 
 # Initialize the model
 model = load_model(params, model_path)
-
-# Initialize the tokenizer
 tokenizer = MistralTokenizer.from_model("pixtral")
 
 @spaces.GPU
@@ -134,18 +138,17 @@ def process_image_and_text(image, prompt):
 
     # Process the image and generate text
     with torch.no_grad():
-        model.cuda()  # Move model to GPU only when processing
+        model.cuda() 
         vision_output = model(image_tensor)
-        model.cpu()  # Move model back to CPU after processing
-        # Add text generation logic here
+        model.cpu()
         generated_text = f"Generated text based on the image and prompt: {prompt}"
 
     return generated_text, len(tokens), len(images)
 
 # Gradio interface
 with gr.Blocks() as demo:
-    gr.Markdown("# Pixtral Image-to-Text Model Demo")
-    gr.Markdown("Upload an image and provide a prompt to generate text based on it.")
+    gr.Markdown(title)
+    gr.Markdown(description)
     
     with gr.Row():
         with gr.Column(scale=1):