Update app.py

app.py

@@ -1,51 +1,49 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-
-title = "🤖AI ChatBot"
+title = "🤖 AI ChatBot"
 description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
 examples = [["How are you?"]]
 
-
 tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
 model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
 
-# tokenizer = AutoTokenizer.from_pretrained("Salesforce/xgen-7b-8k-base", trust_remote_code=True)
-# model = AutoModelForCausalLM.from_pretrained("Salesforce/xgen-7b-8k-base", torch_dtype=torch.bfloat16)
+def generate_response(input_text, chat_history=[]):
+    # Tokenize the new input sentence
+    new_user_input_ids = tokenizer.encode(input_text + tokenizer.eos_token, return_tensors="pt")
 
+    # Append the new user input tokens to the chat history
+    bot_input_ids = torch.cat([torch.tensor(chat_history), new_user_input_ids], dim=-1)
 
-def predict(input, history=[]):
-    # tokenize the new input sentence
-    new_user_input_ids = tokenizer.encode(
-        input + tokenizer.eos_token, return_tensors="pt"
-    )
+    # Generate a response
+    chat_output = model.generate(bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id)
 
-    # append the new user input tokens to the chat history
-    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
+    # Decode the response tokens into text
+    response = tokenizer.decode(chat_output[:, bot_input_ids.shape[-1]:][0], skip_special_tokens=True)
 
-    # generate a response
-    history = model.generate(
-        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
-    ).tolist()
+    return response
 
-    # convert the tokens to text, and then split the responses into lines
-    response = tokenizer.decode(history[0]).split("<|endoftext|>")
-    # print('decoded_response-->>'+str(response))
-    response = [
-        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
-    ]  # convert to tuples of list
-    # print('response-->>'+str(response))
-    return response, history
+def chatbot_interface(input_text):
+    # Generate response based on input text and chat history
+    response = generate_response(input_text, chat_history)
 
+    # Append the input and response to the chat history
+    chat_history.append(tokenizer.encode(input_text + response))
 
-gr.Interface(
-    fn=predict,
+    return response
+
+chat_history = []  # Initialize chat history
+
+iface = gr.Interface(
+    fn=chatbot_interface,
+    inputs=gr.inputs.Textbox(lines=2, label="Chat"),
+    outputs=gr.outputs.Textbox(label="Response"),
+    layout="vertical",
     title=title,
     description=description,
     examples=examples,
-    inputs=["text", "state"],
-    outputs=["chatbot", "state"],
-    # theme="finlaymacklon/boxy_violet",
-    theme="london",
-).launch()
+    theme="london"
+)
+
+iface.launch()