Update app.py

app.py

@@ -1,3 +1,27 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 import gradio as gr
 
-gr.Interface.load("models/microsoft/DialoGPT-large").launch()
+tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
+model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
+
+# Initialize chat history
+chat_history_ids = None
+
+def chat_cpu(user_input):
+    global chat_history_ids
+    # Encode the new user input, add the eos_token, and return a tensor in PyTorch
+    new_user_input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors='pt')
+
+    # Append the new user input tokens to the chat history
+    bot_input_ids = torch.cat([chat_history_ids, new_user_input_ids], dim=-1) if chat_history_ids is not None else new_user_input_ids
+
+    # Generate a response while limiting the total chat history to 1000 tokens
+    chat_history_ids = model.generate(bot_input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+
+    # Pretty print last output tokens from bot
+    response = tokenizer.decode(chat_history_ids[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
+    return "DialoGPT: {}".format(response)
+
+iface = gr.Interface(fn=chat_cpu, inputs="text", outputs="text")
+iface.launch(share=True)