featurebench-lite-modal

v1.0

FeatureBench lite split for Modal: 30 feature-implementation tasks with gpus=1 for GPU tasks (7/30). Use with -e modal. Original benchmark: https://github.com/LiberCoders/FeatureBench.

uvx harbor run -d featurebench-lite-modal@1.0

Tasks (30)

astropy__astropy.b0db0daa.test_quantity_erfa_ufuncs.3fc54395.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t astropy__astropy.b0db0daa.test_quantity_erfa_ufuncs.3fc54395.lv1
HEAD
astropy__astropy.b0db0daa.test_table.48eef659.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t astropy__astropy.b0db0daa.test_table.48eef659.lv1
HEAD
huggingface__transformers.e2e8dbed.test_modeling_seggpt.f9e83f60.lv2
uvx harbor run -d featurebench-lite-modal@1.0 -t huggingface__transformers.e2e8dbed.test_modeling_seggpt.f9e83f60.lv2
HEAD
huggingface__transformers.e2e8dbed.test_processing_wav2vec2.4f660c78.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t huggingface__transformers.e2e8dbed.test_processing_wav2vec2.4f660c78.lv1
HEAD
huggingface__transformers.e2e8dbed.test_serve.4e7860c7.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t huggingface__transformers.e2e8dbed.test_serve.4e7860c7.lv1
HEAD
huggingface__transformers.e2e8dbed.test_tests_fetcher.e1abe0dd.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t huggingface__transformers.e2e8dbed.test_tests_fetcher.e1abe0dd.lv1
HEAD
huggingface__trl.02a34777.test_data_utils.827a9d15.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t huggingface__trl.02a34777.test_data_utils.827a9d15.lv1
HEAD
lightning-ai__pytorch-lightning.126fa6f1.test_connector.825ef3b1.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t lightning-ai__pytorch-lightning.126fa6f1.test_connector.825ef3b1.lv1
HEAD
lightning-ai__pytorch-lightning.126fa6f1.test_data.c8b292af.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t lightning-ai__pytorch-lightning.126fa6f1.test_data.c8b292af.lv1
HEAD
linkedin__liger-kernel.c856fbab.test_fused_neighborhood_attention.78217be4.lv2
uvx harbor run -d featurebench-lite-modal@1.0 -t linkedin__liger-kernel.c856fbab.test_fused_neighborhood_attention.78217be4.lv2
HEAD
linkedin__liger-kernel.c856fbab.test_poly_norm.7b0e3399.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t linkedin__liger-kernel.c856fbab.test_poly_norm.7b0e3399.lv1
HEAD
mlflow__mlflow.93dab383.test_databricks_tracing_utils.8ef44eb4.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mlflow__mlflow.93dab383.test_databricks_tracing_utils.8ef44eb4.lv1
HEAD
mlflow__mlflow.93dab383.test_judge_tool_search_traces.cad8fc4b.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mlflow__mlflow.93dab383.test_judge_tool_search_traces.cad8fc4b.lv1
HEAD
mlflow__mlflow.93dab383.test_responses_agent.072c4133.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mlflow__mlflow.93dab383.test_responses_agent.072c4133.lv1
HEAD
mlflow__mlflow.93dab383.test_serialization.2c029be6.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mlflow__mlflow.93dab383.test_serialization.2c029be6.lv1
HEAD
mlflow__mlflow.93dab383.test_span.69efd376.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mlflow__mlflow.93dab383.test_span.69efd376.lv1
HEAD
mlflow__mlflow.93dab383.test_trace.17fde8b0.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mlflow__mlflow.93dab383.test_trace.17fde8b0.lv1
HEAD
mlflow__mlflow.93dab383.test_validation.2e1c5076.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mlflow__mlflow.93dab383.test_validation.2e1c5076.lv1
HEAD
mwaskom__seaborn.7001ebe7.test_algorithms.1f0181c2.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mwaskom__seaborn.7001ebe7.test_algorithms.1f0181c2.lv1
HEAD
mwaskom__seaborn.7001ebe7.test_regression.ce8c62e2.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mwaskom__seaborn.7001ebe7.test_regression.ce8c62e2.lv1
HEAD
mwaskom__seaborn.7001ebe7.test_statistics.0f2ae277.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t mwaskom__seaborn.7001ebe7.test_statistics.0f2ae277.lv1
HEAD
netflix__metaflow.b390a8d4.test_stub_generator.7bf08c98.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t netflix__metaflow.b390a8d4.test_stub_generator.7bf08c98.lv1
HEAD
pandas-dev__pandas.82fa2715.test_concat.ebe5de39.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t pandas-dev__pandas.82fa2715.test_concat.ebe5de39.lv1
HEAD
pandas-dev__pandas.82fa2715.test_iceberg.85771c70.lv2
uvx harbor run -d featurebench-lite-modal@1.0 -t pandas-dev__pandas.82fa2715.test_iceberg.85771c70.lv2
HEAD
pandas-dev__pandas.82fa2715.test_list_accessor.7ab0b2ea.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t pandas-dev__pandas.82fa2715.test_list_accessor.7ab0b2ea.lv1
HEAD
pydantic__pydantic.e1dcaf9e.test_deprecated_fields.40a2ec54.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t pydantic__pydantic.e1dcaf9e.test_deprecated_fields.40a2ec54.lv1
HEAD
pydata__xarray.97f3a746.test_backends_chunks.fa55f68a.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t pydata__xarray.97f3a746.test_backends_chunks.fa55f68a.lv1
HEAD
pydata__xarray.97f3a746.test_treenode.aa8ba777.lv2
uvx harbor run -d featurebench-lite-modal@1.0 -t pydata__xarray.97f3a746.test_treenode.aa8ba777.lv2
HEAD
sphinx-doc__sphinx.e347e59c.test_domain_c.4068b9e8.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t sphinx-doc__sphinx.e347e59c.test_domain_c.4068b9e8.lv1
HEAD
sympy__sympy.c1097516.test_nullspace.f14fc970.lv1
uvx harbor run -d featurebench-lite-modal@1.0 -t sympy__sympy.c1097516.test_nullspace.f14fc970.lv1
HEAD