app.py

# Import libraries
import os
os.system('pip install transformers torch datasets')
from transformers import GPT2LMHeadModel, GPT2Tokenizer, AdamW
from torch.utils.data import Dataset, DataLoader
from datasets import load_dataset
from torch.nn.utils.rnn import pad_sequence
import torch


dataset = load_dataset("text", data_files={"train": "BotDataset.txt"})

# Tokenization
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")

class MyDataset(Dataset):
    def __init__(self, texts, max_length=512):
        self.texts = texts
        self.max_length = max_length

    def __len__(self):
        return len(self.texts)

    def __getitem__(self, idx):
        # Tokenize the text without squeezing the tensor and convert to Long tensor
        input_ids = tokenizer.encode(self.texts[idx], return_tensors='pt').long()

        # Optionally truncate or pad the sequence to a maximum length
        input_ids = input_ids[:, :self.max_length]

        # If needed, pad the sequence to the max_length using torch.nn.functional.pad
        input_ids = torch.nn.functional.pad(input_ids, (0, self.max_length - input_ids.size(1)), 'constant', 0)

        return {'input_ids': input_ids}

# Create DataLoader without collate_fn
my_dataset = MyDataset(dataset['train']['text'])
dataloader = DataLoader(my_dataset, batch_size=4, shuffle=True)

# Load pre-trained model
model = GPT2LMHeadModel.from_pretrained("gpt2")

# Move model to GPU if available
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

# Define optimizer
optimizer = AdamW(model.parameters(), lr=5e-5)

# Fine-tuning Loop
for epoch in range(4):
    total_loss = 0.0
    for i, batch in enumerate(dataloader):
        batch = {k: v.to(device) for k, v in batch.items()}
        outputs = model(**batch, labels=batch['input_ids'])
        loss = outputs.loss
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()

        total_loss += loss.item()

        if (i + 1) % 100 == 0:  # Print loss every 100 batches
            average_loss = total_loss / 100
            print(f"Epoch: {epoch + 1}, Batch: {i + 1}, Average Loss: {average_loss:.4f}")
            total_loss = 0.0

print("Training complete!")

model.save_pretrained('/gpt2_better')
tokenizer.save_pretrained('/gpt2_better/tokenizer')