Spaces:

Naseer-010
/

DIME

Configuration error

App Files Files Community

DIME / benchmark

67 kB

Ctrl+K

Ctrl+K

5 contributors

History: 2 commits

Naseer-010's picture

added reward function normalization, hidden eval set

15673b8 about 2 months ago

__init__.py

125 Bytes
added canonical evaluation harness, unified DIME index, deterministic replay guarantees about 2 months ago
benchmark_config.py

2.9 kB
added reward function normalization, hidden eval set about 2 months ago
benchmark_registry.py

4 kB
added reward function normalization, hidden eval set about 2 months ago
deterministic.py

4.97 kB
added canonical evaluation harness, unified DIME index, deterministic replay guarantees about 2 months ago
dime_index.py

7.18 kB
added canonical evaluation harness, unified DIME index, deterministic replay guarantees about 2 months ago
evaluation_harness.py

20.3 kB
added reward function normalization, hidden eval set about 2 months ago
hidden_eval_registry.py

2.68 kB
added reward function normalization, hidden eval set about 2 months ago
reward_telemetry.py

8.9 kB
added reward function normalization, hidden eval set about 2 months ago
statistical_report.py

11.5 kB
added reward function normalization, hidden eval set about 2 months ago
utils.py

4.44 kB
added canonical evaluation harness, unified DIME index, deterministic replay guarantees about 2 months ago