-

Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

from fmeval.data_loaders.data_config import DataConfig
from fmeval.constants import MIME_TYPE_JSONLINES

config = DataConfig(
dataset_name="tiny_dataset",
dataset_uri="tiny_dataset.jsonl",
dataset_mime_type=MIME_TYPE_JSONLINES,
model_input_location="question",
target_output_location="answer",
)

def predict(self, prompt: str) → Tuple[Optional[str], Optional[float]]

  1. from dataclasses import dataclass

@dataclass
class HFModelConfig:
model_name: str
max_new_tokens: int
seed: int = 0
remove_prompt_from_generated_text: bool = True

  2. from typing import Tuple, Optional
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from fmeval.model_runners.model_runner import ModelRunner

class HuggingFaceCausalLLMModelRunner(ModelRunner):
def __init__(self, model_config: HFModelConfig):
    self.config = model_config
    self.model = AutoModelForCausalLM.from_pretrained(self.config.model_name)
    self.tokenizer = AutoTokenizer.from_pretrained(self.config.model_name)

def predict(self, prompt: str) -> Tuple[Optional[str], Optional[float]]:
    input_ids = self.tokenizer(prompt, return_tensors="pt").to(self.model.device)
    generations = self.model.generate(
        **input_ids,
        max_new_tokens=self.config.max_new_tokens,
        pad_token_id=self.tokenizer.eos_token_id,
    )
    generation_contains_input = (
        input_ids["input_ids"][0] == generations[0][: input_ids["input_ids"].shape[1]]
    ).all()
    if self.config.remove_prompt_from_generated_text and not generation_contains_input:
        warnings.warn(
            "Your model does not return the prompt as part of its generations. "
            "`remove_prompt_from_generated_text` does nothing."
        )
    if self.config.remove_prompt_from_generated_text and generation_contains_input:
        output = self.tokenizer.batch_decode(generations[:, input_ids["input_ids"].shape[1] :])[0]
    else:
        output = self.tokenizer.batch_decode(generations, skip_special_tokens=True)[0]

    with torch.inference_mode():
        input_ids = self.tokenizer(self.tokenizer.bos_token + prompt, return_tensors="pt")["input_ids"]
        model_output = self.model(input_ids, labels=input_ids)
        probability = -model_output[0].item()

    return output, probability

  3. hf_config = HFModelConfig(model_name="gpt2", max_new_tokens=32)
model = HuggingFaceCausalLLMModelRunner(model_config=hf_config)

    model_output = model.predict("London is the capital of?")[0]
print(model_output)
eval_algo.evaluate_sample()