In addition to alpaca you ll also need

class CustomLLM(LLM):
    model_name = "bertin"
    
    def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
        input = ""
        temperature = 0.1
        device = "cuda"
        top_p = 0.75
        top_k = 40
        num_beams = 4
        max_new_tokens = num_output

        prompt = prompter.generate_prompt(prompt, input)
        inputs = tokenizer(prompt, return_tensors="pt")
        input_ids = inputs["input_ids"].to(device)
        generation_config = GenerationConfig(
          temperature=temperature,
          top_p=top_p,
          top_k=top_k
        )

        with torch.no_grad():
          generation_output = model.generate(
            input_ids=input_ids,
            generation_config=generation_config,
            return_dict_in_generate=True,
            output_scores=True,
            max_new_tokens=max_new_tokens,
          )
        s = generation_output.sequences[0]
        output = tokenizer.decode(s)
        response = prompter.get_response(output)

        print(prompt)
        print(response)

        prompt_length = len(prompt)
        # response = self.pipeline(prompt, max_new_tokens=num_output)[0]["generated_text"]

        # only return newly generated tokens
        return response[prompt_length:]

max_input_size = 2048
num_output = 256
max_chunk_overlap = 20
prompt_helper = PromptHelper(max_input_size, num_output, max_chunk_overlap)