Add files using upload-large-folder tool

lm-evaluation-harness/lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_lug.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: lug
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_lug

lm-evaluation-harness/lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_twi.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: twi
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_twi

lm-evaluation-harness/lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_wol.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: wol
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_wol

lm-evaluation-harness/lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_xho.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: xho
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_xho

lm-evaluation-harness/lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_yor.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: yor
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_yor

lm-evaluation-harness/lm_eval/tasks/afrixnli/lai prompt/translate/afrixnli_manual_translate_zul.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: zul
+include: afrixnli_manual_translate_yaml
+task: afrixnli_manual_translate_zul

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_amh.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: amh
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_amh_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_ewe.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: ewe
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_ewe_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_hau.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: hau
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_hau_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_lin.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: lin
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_lin_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_lug.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: lug
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_lug_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_orm.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: orm
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_orm_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_sot.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: sot
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_sot_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_swa.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: swa
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_swa_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_twi.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: twi
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_twi_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_wol.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: wol
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_wol_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_xho.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: xho
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_xho_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_yaml

@@ -0,0 +1,27 @@
+tag: afrixnli_tt_tasks
+dataset_path: masakhane/afrixnli-translate-test
+dataset_name: null
+output_type: multiple_choice
+test_split: test
+fewshot_split: test
+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-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_yor.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: yor
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_yor_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/afrixnli_translate_zul.yaml

@@ -0,0 +1,15 @@
+# Generated by utils.py
+dataset_name: zul
+doc_to_text: '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?'
+include: afrixnli_translate_yaml
+task: afrixnli_translate_zul_prompt_1

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_1/utils.py

@@ -0,0 +1,19 @@
+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-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_amh.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: amh
+include: afrixnli_translate_yaml
+task: afrixnli_translate_amh_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_ewe.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: ewe
+include: afrixnli_translate_yaml
+task: afrixnli_translate_ewe_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_fra.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: fra
+include: afrixnli_translate_yaml
+task: afrixnli_translate_fra_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_hau.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: hau
+include: afrixnli_translate_yaml
+task: afrixnli_translate_hau_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_ibo.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: ibo
+include: afrixnli_translate_yaml
+task: afrixnli_translate_ibo_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_kin.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: kin
+include: afrixnli_translate_yaml
+task: afrixnli_translate_kin_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_lin.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: lin
+include: afrixnli_translate_yaml
+task: afrixnli_translate_lin_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_lug.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: lug
+include: afrixnli_translate_yaml
+task: afrixnli_translate_lug_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_orm.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: orm
+include: afrixnli_translate_yaml
+task: afrixnli_translate_orm_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_sna.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: sna
+include: afrixnli_translate_yaml
+task: afrixnli_translate_sna_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_sot.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: sot
+include: afrixnli_translate_yaml
+task: afrixnli_translate_sot_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_swa.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: swa
+include: afrixnli_translate_yaml
+task: afrixnli_translate_swa_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_twi.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: twi
+include: afrixnli_translate_yaml
+task: afrixnli_translate_twi_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_wol.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: wol
+include: afrixnli_translate_yaml
+task: afrixnli_translate_wol_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_xho.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: xho
+include: afrixnli_translate_yaml
+task: afrixnli_translate_xho_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_yaml

@@ -0,0 +1,31 @@
+tag: afrixnli_tt_tasks
+dataset_path: masakhane/afrixnli-translate-test
+dataset_name: null
+output_type: multiple_choice
+test_split: test
+fewshot_split: test
+doc_to_text: "{{premise}}\nQuestion: {{hypothesis}} True, False, or Neither?\nAnswer:"
+# True = entailment
+# False = contradiction
+# Neither = neutral
+doc_to_target: !function utils.doc_to_target
+doc_to_choice:
+  - "True"
+  - "Neither"
+  - "False"
+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-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_yor.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: yor
+include: afrixnli_translate_yaml
+task: afrixnli_translate_yor_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/afrixnli_translate_zul.yaml

@@ -0,0 +1,4 @@
+# Generated by utils.py
+dataset_name: zul
+include: afrixnli_translate_yaml
+task: afrixnli_translate_zul_prompt_2

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_2/utils.py

@@ -0,0 +1,6 @@
+from lm_eval.utils import weighted_f1_score
+
+
+def doc_to_target(doc):
+    replacements = {0: "True", 1: "Neither", 2: "False"}
+    return replacements[doc["label"]]

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_amh.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: amh
+doc_to_text: "Given the following premise and hypothesis in Amharic, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_amh_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_ewe.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: ewe
+doc_to_text: "Given the following premise and hypothesis in Ewe, identify if the premise\
+  \ entails, contradicts, or is neutral towards the hypothesis. Please respond with\
+  \ exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}} \n\
+  Hypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_ewe_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_fra.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: fra
+doc_to_text: "Given the following premise and hypothesis in French, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_fra_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_hau.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: hau
+doc_to_text: "Given the following premise and hypothesis in Hausa, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_hau_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_ibo.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: ibo
+doc_to_text: "Given the following premise and hypothesis in Igbo, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_ibo_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_kin.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: kin
+doc_to_text: "Given the following premise and hypothesis in Kinyarwanda, identify\
+  \ if the premise entails, contradicts, or is neutral towards the hypothesis. Please\
+  \ respond with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_kin_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_lin.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: lin
+doc_to_text: "Given the following premise and hypothesis in Lingala, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_lin_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_lug.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: lug
+doc_to_text: "Given the following premise and hypothesis in Luganda, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_lug_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_orm.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: orm
+doc_to_text: "Given the following premise and hypothesis in Oromo, identify if the\
+  \ premise entails, contradicts, or is neutral towards the hypothesis. Please respond\
+  \ with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_orm_prompt_3

lm-evaluation-harness/lm_eval/tasks/afrixnli/translate/prompt_3/afrixnli_translate_sna.yaml

@@ -0,0 +1,8 @@
+# Generated by utils.py
+dataset_name: sna
+doc_to_text: "Given the following premise and hypothesis in chiShona, identify if\
+  \ the premise entails, contradicts, or is neutral towards the hypothesis. Please\
+  \ respond with exact 'entailment', 'contradiction', or 'neutral'. \n\nPremise: {{premise}}\
+  \ \nHypothesis: {{hypothesis}}"
+include: afrixnli_translate_yaml
+task: afrixnli_translate_sna_prompt_3