improve interface

app.py

@@ -2,7 +2,7 @@ import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
 import json
-from globe import title, description, customtool
+from globe import title, description, customtool , presentation1, presentation2, joinus
 import spaces
 
 model_path = "nvidia/Nemotron-Mini-4B-Instruct"
@@ -77,6 +77,13 @@ with gr.Blocks() as demo:
         gr.Markdown(title)
     with gr.Row():
         gr.Markdown(description)    
+    with gr.Row():
+        with gr.Group():
+            gr.Markdown(presentation1)
+        with gr.Group():
+            gr.Markdown(presentation2)
+    with gr.Row():
+        gr.Markdown(joinus)
     with gr.Row():
         with gr.Column(scale=3):
             chatbot = gr.Chatbot(height=400)
@@ -84,7 +91,8 @@ with gr.Blocks() as demo:
             with gr.Row():
                 send = gr.Button("Send")
                 clear = gr.Button("Clear")
-            system_message = gr.Textbox(
+            with gr.Accordion(label="🧪Advanced Settings", open=False):
+                system_message = gr.Textbox(
                 label="System Message",
                 value="You are a helpful AI assistant.",
                 lines=2,

globe.py

@@ -1,26 +1,31 @@
+joinus = """
+## 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 🤗
+"""
+
 title =  """# 🙋🏻‍♂️Welcome to Tonic's 🤖 Nemotron-Mini-4B Demo 🚀"""
 
-description = """Nemotron-Mini-4B-Instruct is a model for generating responses for roleplaying, retrieval augmented generation, and function calling.  It is a small language model (SLM) optimized through distillation, pruning and quantization for speed and on-device deployment. It is a fine-tuned version of [nvidia/Minitron-4B-Base](https://huggingface.co/nvidia/Minitron-4B-Base), which was pruned and distilled from [Nemotron-4 15B](https://arxiv.org/abs/2402.16819) using [our LLM compression technique](https://arxiv.org/abs/2407.14679). This instruct model is optimized for roleplay, RAG QA, and function calling in English. It supports a context length of 4,096 tokens. This model is ready for commercial use.
+description = """🤖Nemotron-Mini-4B-Instruct is a model for generating responses for roleplaying, retrieval augmented generation, and function calling.  It is a small language model (SLM) optimized through distillation, pruning and quantization for speed and on-device deployment. It is a fine-tuned version of [nvidia/Minitron-4B-Base](https://huggingface.co/nvidia/Minitron-4B-Base), which was pruned and distilled from [Nemotron-4 15B](https://arxiv.org/abs/2402.16819) using [our LLM compression technique](https://arxiv.org/abs/2407.14679). This instruct model is optimized for roleplay, RAG QA, and function calling in English. It supports a context length of 4,096 tokens. This model is ready for commercial use.
+"""
 
-Try this model on [build.nvidia.com](https://build.nvidia.com/nvidia/nemotron-mini-4b-instruct).
+presentation1 = """Try this model on [build.nvidia.com](https://build.nvidia.com/nvidia/nemotron-mini-4b-instruct).
 
 **Model Developer:** NVIDIA 
 
-**Model Dates:** Nemotron-Mini-4B-Instruct was trained between February 2024 and Aug 2024.
+**Model Dates:** 🤖Nemotron-Mini-4B-Instruct was trained between February 2024 and Aug 2024.
 
 ## License
 
-[NVIDIA Community Model License](https://huggingface.co/nvidia/Nemotron-Mini-4B-Instruct/blob/main/nvidia-community-model-license-aug2024.pdf)
+[NVIDIA Community Model License](https://huggingface.co/nvidia/Nemotron-Mini-4B-Instruct/blob/main/nvidia-community-model-license-aug2024.pdf)"""
 
+presentation2 = """
 ## Model Architecture
 
 Nemotron-Mini-4B-Instruct uses a model embedding size of 3072, 32 attention heads, and an MLP intermediate dimension of 9216. It also uses Grouped-Query Attention (GQA) and Rotary Position Embeddings (RoPE). 
 
 **Architecture Type:** Transformer Decoder (auto-regressive language model) 
 
-**Network Architecture:** Nemotron-4 
-
-"""
+**Network Architecture:** Nemotron-4 """
 
 customtool = """{
   "name": "custom_tool",