LyricGeneratorModel.py

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

from peft import PeftModel, PeftConfig


class LyricGeneratorModel:
    def __init__(self, repo_id: str):
        config = PeftConfig.from_pretrained(repo_id)
        bnb_config = BitsAndBytesConfig(load_in_8bit=True)
        model = AutoModelForCausalLM.from_pretrained(
            config.base_model_name_or_path,
            return_dict=True,
            quantization_config=bnb_config,
            device_map="auto",
        )
        self.tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
        self.model = PeftModel.from_pretrained(model, repo_id)

    def generate_lyrics(self, prompt: str, max_length: int):
        input_ids = self.tokenizer(prompt, return_tensors="pt").input_ids
        input_ids = input_ids.to("cuda")

        output_tokens = self.model.generate(
            input_ids, do_sample=True, max_length=max_length
        )

        output_text = self.tokenizer.batch_decode(output_tokens)[0]

        return output_text