LICENSE.md
LICENSE_NOTES.md
MANIFEST.in
NOTICE
README.md
pyproject.toml
slm_eval/__init__.py
slm_eval/__main__.py
slm_eval/defaults.py
slm_eval/eval_avg.py
slm_eval/evaluator.py
slm_eval/evaluator_utils.py
slm_eval/int_index.py
slm_eval/result_schema.py
slm_eval/utils.py
slm_eval.egg-info/PKG-INFO
slm_eval.egg-info/SOURCES.txt
slm_eval.egg-info/dependency_links.txt
slm_eval.egg-info/entry_points.txt
slm_eval.egg-info/requires.txt
slm_eval.egg-info/top_level.txt
slm_eval/_cli/__init__.py
slm_eval/_cli/harness.py
slm_eval/_cli/ls.py
slm_eval/_cli/run.py
slm_eval/_cli/subcommand.py
slm_eval/_cli/utils.py
slm_eval/_cli/validate.py
slm_eval/api/__init__.py
slm_eval/api/filter.py
slm_eval/api/group.py
slm_eval/api/instance.py
slm_eval/api/metrics.py
slm_eval/api/model.py
slm_eval/api/registry.py
slm_eval/api/samplers.py
slm_eval/api/task.py
slm_eval/api/utils.py
slm_eval/caching/__init__.py
slm_eval/caching/cache.py
slm_eval/config/__init__.py
slm_eval/config/evaluate_config.py
slm_eval/config/group.py
slm_eval/config/task.py
slm_eval/decontamination/__init__.py
slm_eval/decontamination/archiver.py
slm_eval/decontamination/decontaminate.py
slm_eval/decontamination/janitor.py
slm_eval/filters/__init__.py
slm_eval/filters/custom.py
slm_eval/filters/decontamination.py
slm_eval/filters/extraction.py
slm_eval/filters/selection.py
slm_eval/filters/transformation.py
slm_eval/loggers/__init__.py
slm_eval/loggers/evaluation_tracker.py
slm_eval/loggers/trackio_logger.py
slm_eval/loggers/utils.py
slm_eval/loggers/wandb_logger.py
slm_eval/models/__init__.py
slm_eval/models/_onnx_base.py
slm_eval/models/anthropic_llms.py
slm_eval/models/api_models.py
slm_eval/models/dummy.py
slm_eval/models/gguf.py
slm_eval/models/hf_audiolm.py
slm_eval/models/hf_steered.py
slm_eval/models/hf_vlms.py
slm_eval/models/huggingface.py
slm_eval/models/ibm_watsonx_ai.py
slm_eval/models/litellm_llms.py
slm_eval/models/mamba_lm.py
slm_eval/models/megatron_lm.py
slm_eval/models/mistral3.py
slm_eval/models/nemo_lm.py
slm_eval/models/neuron_optimum.py
slm_eval/models/onnxruntime_genai.py
slm_eval/models/onnxruntime_ort.py
slm_eval/models/openai_completions.py
slm_eval/models/optimum_habana.py
slm_eval/models/optimum_ipex.py
slm_eval/models/optimum_lm.py
slm_eval/models/sglang_causallms.py
slm_eval/models/sglang_generate_API.py
slm_eval/models/textsynth.py
slm_eval/models/trtllm_causallms.py
slm_eval/models/utils.py
slm_eval/models/utils_hf.py
slm_eval/models/vllm_causallms.py
slm_eval/models/vllm_vlms.py
slm_eval/models/winml.py
slm_eval/prompts/__init__.py
slm_eval/tasks/README.md
slm_eval/tasks/__init__.py
slm_eval/tasks/_factory.py
slm_eval/tasks/_index.py
slm_eval/tasks/_yaml_loader.py
slm_eval/tasks/manager.py
slm_eval/tasks/__pycache__/__init__.cpython-312.pyc
slm_eval/tasks/__pycache__/_factory.cpython-312.pyc
slm_eval/tasks/__pycache__/_index.cpython-312.pyc
slm_eval/tasks/__pycache__/_yaml_loader.cpython-312.pyc
slm_eval/tasks/__pycache__/manager.cpython-312.pyc
slm_eval/tasks/slm/CONVENTIONS.md
slm_eval/tasks/slm/__init__.py
slm_eval/tasks/slm/_shared.py
slm_eval/tasks/slm/__pycache__/__init__.cpython-312.pyc
slm_eval/tasks/slm/__pycache__/_shared.cpython-312.pyc
slm_eval/tasks/slm/arc_challenge/README.md
slm_eval/tasks/slm/arc_challenge/arc_challenge.yaml
slm_eval/tasks/slm/arc_challenge/utils.py
slm_eval/tasks/slm/arc_challenge/__pycache__/utils.cpython-312.pyc
slm_eval/tasks/slm/arc_easy/README.md
slm_eval/tasks/slm/arc_easy/arc_easy.yaml
slm_eval/tasks/slm/arc_easy/utils.py
slm_eval/tasks/slm/arc_easy/__pycache__/utils.cpython-312.pyc
slm_eval/tasks/slm/arithmark_2/README.md
slm_eval/tasks/slm/arithmark_2/arithmark_2.yaml
slm_eval/tasks/slm/arithmark_2/utils.py
slm_eval/tasks/slm/arithmark_2/__pycache__/utils.cpython-312.pyc
slm_eval/tasks/slm/arithmark_3_0/README.md
slm_eval/tasks/slm/arithmark_3_0/arithmark_3_0.yaml
slm_eval/tasks/slm/arithmark_3_0/utils.py
slm_eval/tasks/slm/arithmark_3_0/__pycache__/utils.cpython-312.pyc
slm_eval/tasks/slm/bfcl_v4/README.md
slm_eval/tasks/slm/bfcl_v4/bfcl_v4.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_irrelevance.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_multi_turn_base.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_multi_turn_long_context.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_multi_turn_miss_func.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_multi_turn_miss_param.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_multiple.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_parallel.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_parallel_multiple.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_simple_java.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_simple_javascript.yaml
slm_eval/tasks/slm/bfcl_v4/bfcl_v4_simple_python.yaml
slm_eval/tasks/slm/bfcl_v4/utils.py
slm_eval/tasks/slm/bfcl_v4/__pycache__/utils.cpython-312.pyc
slm_eval/tasks/slm/gpqa_diamond/README.md
slm_eval/tasks/slm/gpqa_diamond/gpqa_diamond.yaml
slm_eval/tasks/slm/gpqa_diamond/utils.py
slm_eval/tasks/slm/gpqa_diamond/__pycache__/utils.cpython-312.pyc
slm_eval/tasks/slm/hellaswag/README.md
slm_eval/tasks/slm/hellaswag/hellaswag.yaml
slm_eval/tasks/slm/hellaswag/utils.py
slm_eval/tasks/slm/hellaswag/__pycache__/utils.cpython-312.pyc
slm_eval/tasks/slm/int_index/README.md
slm_eval/tasks/slm/int_index/int_index.yaml
slm_eval/tasks/slm/math_500/README.md
slm_eval/tasks/slm/math_500/math_500.yaml
slm_eval/tasks/slm/math_500/utils.py
slm_eval/tasks/slm/math_500/__pycache__/utils.cpython-312.pyc
tests/test_eval_avg.py
tests/test_scoring.py
tests/test_task_registry.py