app.py

import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer, Trainer, TrainingArguments
from datasets import load_dataset

# Load and prepare the dataset
dataset = load_dataset("daily_dialog")

tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-small")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-small")

# Define training arguments
training_args = TrainingArguments(
    output_dir="./results",
    num_train_epochs=3,
    per_device_train_batch_size=4,
    per_device_eval_batch_size=4,
    warmup_steps=500,
    weight_decay=0.01,
    logging_dir='./logs',
    logging_steps=10,
)

# Prepare the data for training
def tokenize_function(examples):
    return tokenizer(examples["text"], padding="max_length", truncation=True)

tokenized_datasets = dataset.map(tokenize_function, batched=True)

# Initialize the Trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_datasets["train"],
    eval_dataset=tokenized_datasets["test"]
)

# Training the model
trainer.train()

# Streamlit interface
st.title('Simple Chatbot')
user_input = st.text_input("You: ")

if user_input:
    # Encode the user input and generate a response
    inputs = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors='pt')
    reply_ids = model.generate(inputs, max_length=1000, pad_token_id=tokenizer.eos_token_id)
    reply = tokenizer.decode(reply_ids[0], skip_special_tokens=True)

    st.write("Bot:", reply)