| import torch | |
| from transformers import GPT2LMHeadModel, GPT2Tokenizer | |
| # Load the pre-trained models and tokenizers | |
| wormgpt_model = GPT2LMHeadModel.from_pretrained("wormgpt") | |
| wormgpt_tokenizer = GPT2Tokenizer.from_pretrained("wormgpt") | |
| fraudgpt_model = GPT2LMHeadModel.from_pretrained("fraudgpt") | |
| fraudgpt_tokenizer = GPT2Tokenizer.from_pretrained("fraudgpt") | |
| xxxgpt_model = GPT2LMHeadModel.from_pretrained("xxxgpt") | |
| xxxgpt_tokenizer = GPT2Tokenizer.from_pretrained("xxxgpt") | |
| evilgpt_model = GPT2LMHeadModel.from_pretrained("evilgpt") | |
| evilgpt_tokenizer = GPT2Tokenizer.from_pretrained("evilgpt") | |
| # Function to generate text from a given prompt using the specified model | |
| def generate_text(prompt, model, tokenizer, max_length=50): | |
| input_ids = tokenizer.encode(prompt, return_tensors="pt") | |
| output = model.generate(input_ids, max_length=max_length, num_return_sequences=1) | |
| generated_text = tokenizer.decode(output[0], skip_special_tokens=True) | |
| return generated_text | |
| # Function to generate text from a given prompt using all four models | |
| def generate_uncensored_text(prompt, max_length=50): | |
| wormgpt_text = generate_text(prompt, wormgpt_model, wormgpt_tokenizer, max_length) | |
| fraudgpt_text = generate_text(prompt, fraudgpt_model, fraudgpt_tokenizer, max_length) | |
| xxxgpt_text = generate_text(prompt, xxxgpt_model, xxxgpt_tokenizer, max_length) | |
| evilgpt_text = generate_text(prompt, evilgpt_model, evilgpt_tokenizer, max_length) | |
| return wormgpt_text + "\n" + fraudgpt_text + "\n" + xxxgpt_text + "\n" + evilgpt_text | |
| # Example usage | |
| prompt = "I want to generate some uncensored text." | |
| uncensored_text = generate_uncensored_text(prompt) | |
| print(uncensored_text) |