From the beginning :_)

app.py

@@ -1,58 +1,22 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import pipeline
 
-# Load the model and tokenizer
-tokenizer = AutoTokenizer.from_pretrained(
-    "SebastianSchramm/UniNER-7B-type-GPTQ-4bit-128g-actorder_True", 
-    legacy=False
-)
-model = AutoModelForCausalLM.from_pretrained(
-    "SebastianSchramm/UniNER-7B-type-GPTQ-4bit-128g-actorder_True",
-    device_map="auto"
-)
+# Load the model
+chatbot = pipeline("text-generation", model="EleutherAI/gpt-neo-1.3B")
 
-# Define a function to handle user input and generate a response
-def chatbot_response(user_input, chat_history=[]):
-    # Append user input to chat history
-    chat_history.append(("User", user_input))
-    
-    # Prepare the prompt based on the chat history
-    prompt = " ".join([f"{speaker}: {text}" for speaker, text in chat_history])
-    
-    # Generate a response
-    inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(inputs.input_ids, max_length=200, num_return_sequences=1)
-    bot_response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    
-    # Append bot response to chat history
-    chat_history.append(("Bot", bot_response))
-    
-    # Return updated chat history
-    return chat_history, chat_history
+# Define the chatbot function
+def chat(input_text):
+    response = chatbot(input_text, max_length=100, do_sample=True)
+    return response[0]["generated_text"]
 
-# Gradio interface
-with gr.Blocks() as interface:
-    gr.Markdown("### Chat with Your LLM")
-
-    chat_history = gr.State([])  # To store the conversation history
-    chat_display = gr.Chatbot()  # Chat display for the conversation
-    user_input = gr.Textbox(
-        show_label=False, 
-        placeholder="Type your message and press Enter"
-    )
-    send_button = gr.Button("Send")
-    
-    # Define the interaction
-    send_button.click(
-        chatbot_response, 
-        inputs=[user_input, chat_history], 
-        outputs=[chat_display, chat_history]
-    )
-    user_input.submit(
-        chatbot_response, 
-        inputs=[user_input, chat_history], 
-        outputs=[chat_display, chat_history]
-    )
+# Create the Gradio interface
+interface = gr.Interface(
+    fn=chat,
+    inputs="text",
+    outputs="text",
+    title="Chat with an LLM",
+    description="Type your message and chat with the LLM!"
+)
 
-# Launch the Gradio app
+# Launch the app
 interface.launch()

requirements.txt

@@ -1,8 +1,2 @@
-flask
-gradio
 transformers
-torch
-torchvision
-torchaudio
-accelerate>=0.26.0
-optimum
+gradio