LICENSE
README.md
pyproject.toml
llm_behavior_eval/__init__.py
llm_behavior_eval/__main__.py
llm_behavior_eval/evaluate.py
llm_behavior_eval/presets.py
llm_behavior_eval.egg-info/PKG-INFO
llm_behavior_eval.egg-info/SOURCES.txt
llm_behavior_eval.egg-info/dependency_links.txt
llm_behavior_eval.egg-info/entry_points.txt
llm_behavior_eval.egg-info/requires.txt
llm_behavior_eval.egg-info/top_level.txt
llm_behavior_eval/evaluation_utils/base_evaluator.py
llm_behavior_eval/evaluation_utils/censorship_utils.py
llm_behavior_eval/evaluation_utils/custom_dataset.py
llm_behavior_eval/evaluation_utils/dataset_config.py
llm_behavior_eval/evaluation_utils/enums.py
llm_behavior_eval/evaluation_utils/eval_config.py
llm_behavior_eval/evaluation_utils/eval_engine.py
llm_behavior_eval/evaluation_utils/evaluate_factory.py
llm_behavior_eval/evaluation_utils/free_text_bias_evaluator.py
llm_behavior_eval/evaluation_utils/free_text_censorship_evaluator.py
llm_behavior_eval/evaluation_utils/free_text_hallu_evaluator.py
llm_behavior_eval/evaluation_utils/free_text_injection_evaluator.py
llm_behavior_eval/evaluation_utils/free_text_refusal_evaluator.py
llm_behavior_eval/evaluation_utils/max_batch_size.py
llm_behavior_eval/evaluation_utils/prompts.py
llm_behavior_eval/evaluation_utils/refusal_utils.py
llm_behavior_eval/evaluation_utils/sampling_config.py
llm_behavior_eval/evaluation_utils/transformers_eval_engine.py
llm_behavior_eval/evaluation_utils/util_functions.py
llm_behavior_eval/evaluation_utils/vllm_config.py
llm_behavior_eval/evaluation_utils/vllm_eval_engine.py
llm_behavior_eval/evaluation_utils/vllm_types.py
tests/test_base_evaluator.py
tests/test_bloom.py
tests/test_collator.py
tests/test_dataset.py
tests/test_dataset_config.py
tests/test_dataset_identity.py
tests/test_deploy_docs_workflow.py
tests/test_eval_engines.py
tests/test_evaluate_cli.py
tests/test_free_text_censorship_evaluator.py
tests/test_free_text_utils.py
tests/test_mlflow_integration.py
tests/test_util_functions.py