Create app.py

app.py

@@ -0,0 +1,59 @@
+from transformers import GPT2Tokenizer, GPT2LMHeadModel, Trainer, TrainingArguments
+from datasets import load_dataset
+import torch
+
+# Load the pre-trained GPT-2 model and tokenizer
+model_name = "gpt2"
+tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPT2LMHeadModel.from_pretrained(model_name)
+
+# Load your custom dataset (replace 'path_to_dataset' with your dataset path)
+# Dataset format should be a text file with one example per line.
+dataset = load_dataset("text", data_files={"train": "path_to_train.txt", "test": "path_to_test.txt"})
+
+# Tokenize the dataset
+def tokenize_function(examples):
+    return tokenizer(examples["text"], truncation=True, padding="max_length", max_length=128)
+
+tokenized_datasets = dataset.map(tokenize_function, batched=True, remove_columns=["text"])
+
+# Set up data collator (for padding batch sizes)
+from transformers import DataCollatorForLanguageModeling
+data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
+
+# Define training arguments
+training_args = TrainingArguments(
+    output_dir="./results",
+    overwrite_output_dir=True,
+    num_train_epochs=3,
+    per_device_train_batch_size=8,
+    save_steps=500,
+    save_total_limit=2,
+    prediction_loss_only=True,
+    logging_dir="./logs",
+    learning_rate=5e-5,
+    warmup_steps=500,
+    weight_decay=0.01,
+    fp16=torch.cuda.is_available(),
+    evaluation_strategy="steps",
+    eval_steps=500
+)
+
+# Initialize Trainer
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_datasets["train"],
+    eval_dataset=tokenized_datasets["test"],
+    tokenizer=tokenizer,
+    data_collator=data_collator,
+)
+
+# Fine-tune the model
+trainer.train()
+
+# Save the fine-tuned model
+trainer.save_model("./fine_tuned_gpt2")
+tokenizer.save_pretrained("./fine_tuned_gpt2")
+
+print("Model fine-tuned and saved successfully!")