Create app.py

app.py

@@ -0,0 +1,76 @@
+from transformers import GPT2LMHeadModel, GPT2Tokenizer, AdamW
+from torch.utils.data import Dataset, DataLoader
+from datasets import load_dataset
+import torch
+
+# Load Ultrachat dataset
+dataset = load_dataset("HuggingFaceH4/ultrachat_200k", split="train_sft")
+
+# Tokenization
+tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
+
+class MyDataset(Dataset):
+    def __init__(self, data, max_length=1024):
+        self.data = data
+        self.max_length = max_length
+
+    def __len__(self):
+        return len(self.data)
+
+    def __getitem__(self, idx):
+        # Extract relevant information from the user and assistant messages
+        user_content = self.data[idx][0]['content'] if 'content' in self.data[idx][0] else ""
+        assistant_content = self.data[idx][1]['content'] if 'content' in self.data[idx][1] else ""
+
+        # Combine user and assistant messages into a single text
+        text = f"User: {user_content} Assistant: {assistant_content}"
+
+        # Tokenize the text without squeezing the tensor and convert to Long tensor
+        input_ids = tokenizer.encode(text, 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['messages'])
+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("cpu")
+model.to(device)
+
+# Define optimizer
+optimizer = AdamW(model.parameters(), lr=5e-5)
+
+# Fine-tuning Loop
+for epoch in range(1):
+    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_finetuned')
+tokenizer.save_pretrained('/gpt2_finetuned/tokenizer')
+
+print("Model Saved! \n Enjoy the model Now!")