Merge branch 'main' into humaneval

# Conflicts:
#	lm_eval/api/task.py

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_yaml

+group:
+    - afrixnli
+    - afrixnli_manual_direct
+dataset_path: masakhane/afrixnli
+dataset_name: null
+output_type: multiple_choice
+validation_split: validation
+test_split: test
+fewshot_split: validation
+doc_to_text: !function utils.doc_to_text
+doc_to_target: !function utils.doc_to_target
+doc_to_choice:
+  - "entailment"
+  - "neutral"
+  - "contradiction"
+should_decontaminate: true
+doc_to_decontamination_query: premise
+metric_list:
+  - metric: f1
+    aggregation: !function utils.weighted_f1_score
+    average: weighted
+    higher_is_better: True
+    ignore_case: true
+    ignore_punctuation: true
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+metadata:
+  version: 1.0

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_yor.yaml

+# Generated by utils.py
+dataset_name: yor
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_yor

lm_eval/tasks/afrixnli/lai prompt/direct/afrixnli_manual_direct_zul.yaml

+# Generated by utils.py
+dataset_name: zul
+include: afrixnli_manual_direct_yaml
+task: afrixnli_manual_direct_zul

lm_eval/tasks/afrixnli/lai prompt/direct/utils.py

+from lm_eval.utils import weighted_f1_score
+
+
+def doc_to_text(doc):
+    output = """Please identify whether the premise entails or contradicts the hypothesis in the following premise
+    and hypothesis. The answer should be exact entailment, contradiction, or neutral.
+
+    Premise: {premise}
+    Hypothesis: {hypothesis}
+
+    Is it entailment, contradiction, or neutral?"""
+
+    text = output.format(premise=doc["premise"], hypothesis=doc["hypothesis"])
+    return text
+
+
+def doc_to_target(doc):
+    replacements = {0: "entailment", 1: "neutral", 2: "contradiction"}
+    return replacements[doc["label"]]

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_amh.yaml

+# Generated by utils.py
+dataset_name: amh
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_amh

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_ewe.yaml

+# Generated by utils.py
+dataset_name: ewe
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_ewe

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_fra.yaml

+# Generated by utils.py
+dataset_name: fra
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_fra

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_hau.yaml

+# Generated by utils.py
+dataset_name: hau
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_hau

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_ibo.yaml

+# Generated by utils.py
+dataset_name: ibo
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_ibo

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_kin.yaml

+# Generated by utils.py
+dataset_name: kin
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_kin

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_lin.yaml

+# Generated by utils.py
+dataset_name: lin
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_lin

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_lug.yaml

+# Generated by utils.py
+dataset_name: lug
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_lug

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_orm.yaml

+# Generated by utils.py
+dataset_name: orm
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_orm

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_sna.yaml

+# Generated by utils.py
+dataset_name: sna
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_sna

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_sot.yaml

+# Generated by utils.py
+dataset_name: sot
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_sot

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_swa.yaml

+# Generated by utils.py
+dataset_name: swa
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_swa

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_twi.yaml

+# Generated by utils.py
+dataset_name: twi
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_twi

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_wol.yaml

+# Generated by utils.py
+dataset_name: wol
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_wol

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_xho.yaml

+# Generated by utils.py
+dataset_name: xho
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_xho

lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_yaml

+group:
+    - afrixnli
+    - afrixnli_manual_direct
+dataset_path: masakhane/afrixnli-translate-test
+dataset_name: null
+output_type: multiple_choice
+test_split: test
+doc_to_text: !function utils.doc_to_text
+doc_to_target: !function utils.doc_to_target
+doc_to_choice:
+  - "entailment"
+  - "neutral"
+  - "contradiction"
+should_decontaminate: true
+doc_to_decontamination_query: premise
+metric_list:
+  - metric: f1
+    aggregation: !function utils.weighted_f1_score
+    average: weighted
+    higher_is_better: True
+    ignore_case: true
+    ignore_punctuation: true
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+    ignore_case: true
+    ignore_punctuation: true
+metadata:
+  version: 1.0