Add apllication files

app.py

@@ -0,0 +1,54 @@
+import gradio as gr
+from transformers import pipeline
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+import tensorflow
+import torch
+import random
+import time
+import os
+
+
+global default_model_name
+default_model_name = "google/flan-t5-base"
+
+
+def predict(input_text, model_name):
+    if model_name == "":
+        model_name = default_model_name
+
+    pipe = pipeline("text2text-generation", model=model_name)
+    generated_text = pipe(input_text, max_new_tokens=1000)
+
+    return generated_text[0]['generated_text']
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(
+    """
+    # Chatbot to interact with different Large Language Models (LLMs) 
+    [Here](https://huggingface.co/models?pipeline_tag=text2text-generation) are some popular text2text large lamguage models.  
+    Or use default model **"google/flan-t5-base"**
+    """)
+    input_model = gr.Textbox(label="Enter a custom Large Language Model name (LLM):")
+    chatbot = gr.Chatbot(height=300, label="A chatbot to interact with llm", avatar_images=((os.path.join(os.path.dirname(__file__), "user.png")), (os.path.join(os.path.dirname(__file__), "bot.png"))))
+    user_input = gr.Textbox()
+    clear = gr.ClearButton([user_input, chatbot, input_model])
+    
+    def user(user_message, chat_history):
+        return "", chat_history + [[user_message, None]]
+
+    def respond(chat_history, input_model):
+        bot_message = predict(chat_history[-1][0], input_model)
+        chat_history[-1][1] = bot_message
+        time.sleep(2)
+        return chat_history
+    
+    user_input.submit(user, [user_input, chatbot], [user_input, chatbot], queue=False).then(
+                    respond, [chatbot, input_model], chatbot
+    )
+    
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+demo.queue()
+demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+gradio
+tensorflow
+tensorflow_intel
+torch
+transformers