Merge pull request #864 from EleutherAI/add-fewshot-config

[Refactor] CMMLU, C-Eval port ; Add fewshot config

lm_eval/tasks/cmmlu/cmmlu_default_professional_psychology.yaml

+"dataset_name": "professional_psychology"
+"description": "以下是关于专业心理学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_professional_psychology"

lm_eval/tasks/cmmlu/cmmlu_default_public_relations.yaml

+"dataset_name": "public_relations"
+"description": "以下是关于公共关系的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_public_relations"

lm_eval/tasks/cmmlu/cmmlu_default_security_study.yaml

+"dataset_name": "security_study"
+"description": "以下是关于安全研究的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_security_study"

lm_eval/tasks/cmmlu/cmmlu_default_sociology.yaml

+"dataset_name": "sociology"
+"description": "以下是关于社会学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_sociology"

lm_eval/tasks/cmmlu/cmmlu_default_sports_science.yaml

+"dataset_name": "sports_science"
+"description": "以下是关于体育学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_sports_science"

lm_eval/tasks/cmmlu/cmmlu_default_traditional_chinese_medicine.yaml

+"dataset_name": "traditional_chinese_medicine"
+"description": "以下是关于中医中药的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_traditional_chinese_medicine"

lm_eval/tasks/cmmlu/cmmlu_default_virology.yaml

+"dataset_name": "virology"
+"description": "以下是关于病毒学的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_virology"

lm_eval/tasks/cmmlu/cmmlu_default_world_history.yaml

+"dataset_name": "world_history"
+"description": "以下是关于世界历史的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_world_history"

lm_eval/tasks/cmmlu/cmmlu_default_world_religions.yaml

+"dataset_name": "world_religions"
+"description": "以下是关于世界宗教的单项选择题，请直接给出正确答案的选项。\n\n"
+"include": "_default_template_yaml"
+"task": "cmmlu_world_religions"

lm_eval/tasks/crows_pairs/README.md

@@ -93,10 +93,9 @@ All tasks evaluate the percentage of more-stereotypical sentences that are rated
 * [x] Is the task an existing benchmark in the literature?
   * [x] Have you referenced the original paper that introduced the task?
   * [x] If yes, does the original paper provide a reference implementation?
-    * [x] The original paper does not for causal language models, so
+    * [x] The original paper does not for causal language models, so this is a novel formulation of the task for autoregressive LMs.
 
 If other tasks on this dataset are already supported:
 * [x] Is the "Main" variant of this task clearly denoted?
 * [x] Have you provided a short sentence in a README on what each new variant adds / evaluates?
 * [x] Have you noted which, if any, published evaluation setups are matched by this variant?
-  * [x] This matches the evaluations performed in the [Pythia paper](https://arxiv.org/abs/2304.01373)

lm_eval/tasks/storycloze/storycloze_2018.yaml

 group: storycloze
-task: storycloze_2016
+task: storycloze_2018
 dataset_path: story_cloze
 dataset_name: 2018
 output_type: multiple_choice