Create app.py

app.py

@@ -0,0 +1,50 @@
+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)