0
Jump into concepts and practice - no test required
Recommended
from transformers import AutoModelForCausalLM, AutoTokenizer, Trainer, TrainingArguments import torch # Load base model and tokenizer model_name = 'gpt2' tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained(model_name) # Example prompt engineering: adding clear instructions prompt = "Answer the question precisely and concisely:\nWhat is the capital of France?" inputs = tokenizer(prompt, return_tensors='pt') outputs = model.generate(**inputs, max_length=50) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) # If prompt engineering is not enough, fine-tune with small dataset train_texts = ["What is the capital of France?\tParis", "Who wrote Hamlet?\tShakespeare"] train_encodings = tokenizer(train_texts, truncation=True, padding=True) class SimpleDataset(torch.utils.data.Dataset): def __init__(self, encodings): self.encodings = encodings def __len__(self): return len(self.encodings['input_ids']) def __getitem__(self, idx): item = {key: torch.tensor(val[idx]) for key, val in self.encodings.items()} item['labels'] = item['input_ids'].clone() return item dataset = SimpleDataset(train_encodings) training_args = TrainingArguments( output_dir='./results', num_train_epochs=3, per_device_train_batch_size=2, logging_steps=10, save_steps=10, save_total_limit=1, learning_rate=5e-5, weight_decay=0.01, logging_dir='./logs', no_cuda=True ) trainer = Trainer( model=model, args=training_args, train_dataset=dataset ) trainer.train() # After fine-tuning, test again prompt_ft = "What is the capital of France?" inputs_ft = tokenizer(prompt_ft, return_tensors='pt') outputs_ft = model.generate(**inputs_ft, max_length=50) print(tokenizer.decode(outputs_ft[0], skip_special_tokens=True))
Before: Accuracy 60%, Relevance 65%
After prompt engineering: Accuracy 75%, Relevance 78%
After fine-tuning: Accuracy 85%, Relevance 88%