OpenCompass/opencompass/openicl
Junnan Liu 8e8d4f1c64
[Feature] Support G-Pass@k and LiveMathBench (#1772)
* support G-Pass@k and livemathbench

* fix bugs

* fix comments of GPassKEvaluator

* update saved details of GPassKEvaluator

* update saved details of GPassKEvaluator

* fix eval api configs & update openai_api for ease of debugging

* update huggingface path

* fix method name of G-Pass@k

* fix default value of eval_model_name

* refactor G-Pass@k evaluator

* log generation params for each backend

* fix evaluation resume

* add notimplementerror
2024-12-30 16:59:39 +08:00
..
icl_evaluator [Feature] Support G-Pass@k and LiveMathBench (#1772) 2024-12-30 16:59:39 +08:00
icl_inferencer [Fix] Compatible with old versions (#1616) 2024-10-21 10:16:29 +08:00
icl_retriever [Feature] Fullbench v0.1 language update (#1463) 2024-08-28 14:01:05 +08:00
utils [Enhancement] Test linting in CI and fix existing linting errors (#69) 2023-07-17 15:59:10 +08:00
__init__.py [Enhancement] Test linting in CI and fix existing linting errors (#69) 2023-07-17 15:59:10 +08:00
icl_dataset_reader.py [Sync] Initial support of subjective evaluation (#421) 2023-09-22 15:42:31 +08:00
icl_prompt_template.py [Sync] update taco (#1030) 2024-04-09 17:50:23 +08:00