After that, simply run the pipeline and save the results.
import lighteval
from lighteval.logging.evaluation_tracker import EvaluationTracker
from lighteval.models.vllm.vllm_model import VLLMModelConfig
from lighteval.pipeline import ParallelismManager, Pipeline, PipelineParameters
from lighteval.utils.utils import EnvConfig
from lighteval.utils.imports import is_accelerate_available
if is_accelerate_available():
from datetime import timedelta
from accelerate import Accelerator, InitProcessGroupKwargs
accelerator = Accelerator(kwargs_handlers=[InitProcessGroupKwargs(timeout=timedelta(seconds=3000))])
else:
accelerator = None
def main():
evaluation_tracker = EvaluationTracker(
output_dir="./results",
save_details=True,
push_to_hub=True,
hub_results_org="your user name",
)
pipeline_params = PipelineParameters(
launcher_type=ParallelismManager.ACCELERATE,
env_config=EnvConfig(cache_dir="tmp/"),
custom_task_directory=None,
override_batch_size=1,
max_samples=10
)
model_config = VLLMModelConfig(
model_name="HuggingFaceH4/zephyr-7b-beta",
dtype="float16",
use_chat_template=True,
)
task = "helm|mmlu|5|1"
pipeline = Pipeline(
tasks=task,
pipeline_parameters=pipeline_params,
evaluation_tracker=evaluation_tracker,
model_config=model_config,
)
pipeline.evaluate()
pipeline.save_and_push_results()
pipeline.show_results()
if __name__ == "__main__":
main()
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4