Merge branch 'main' into tasklist

# Conflicts:
#	pyproject.toml

lm_eval/tasks/multiblimp/multiblimp_tpn.yaml

+include: _template_yaml
+dataset_name: tpn
+task: multiblimp_tpn

lm_eval/tasks/multiblimp/multiblimp_ttc.yaml

+include: _template_yaml
+dataset_name: ttc
+task: multiblimp_ttc

lm_eval/tasks/multiblimp/multiblimp_tur.yaml

+include: _template_yaml
+dataset_name: tur
+task: multiblimp_tur

lm_eval/tasks/multiblimp/multiblimp_uig.yaml

+include: _template_yaml
+dataset_name: uig
+task: multiblimp_uig

lm_eval/tasks/multiblimp/multiblimp_ukr.yaml

+include: _template_yaml
+dataset_name: ukr
+task: multiblimp_ukr

lm_eval/tasks/multiblimp/multiblimp_urb.yaml

+include: _template_yaml
+dataset_name: urb
+task: multiblimp_urb

lm_eval/tasks/multiblimp/multiblimp_urd.yaml

+include: _template_yaml
+dataset_name: urd
+task: multiblimp_urd

lm_eval/tasks/multiblimp/multiblimp_uzb.yaml

+include: _template_yaml
+dataset_name: uzb
+task: multiblimp_uzb

lm_eval/tasks/multiblimp/multiblimp_vep.yaml

+include: _template_yaml
+dataset_name: vep
+task: multiblimp_vep

lm_eval/tasks/multiblimp/multiblimp_wbp.yaml

+include: _template_yaml
+dataset_name: wbp
+task: multiblimp_wbp

lm_eval/tasks/multiblimp/multiblimp_wol.yaml

+include: _template_yaml
+dataset_name: wol
+task: multiblimp_wol

lm_eval/tasks/multiblimp/multiblimp_xcl.yaml

+include: _template_yaml
+dataset_name: xcl
+task: multiblimp_xcl

lm_eval/tasks/multiblimp/multiblimp_xnr.yaml

+include: _template_yaml
+dataset_name: xnr
+task: multiblimp_xnr

lm_eval/tasks/multiblimp/multiblimp_xpg.yaml

+include: _template_yaml
+dataset_name: xpg
+task: multiblimp_xpg

lm_eval/tasks/multiblimp/multiblimp_yrl.yaml

+include: _template_yaml
+dataset_name: yrl
+task: multiblimp_yrl

lm_eval/tasks/mutual/mutual.yaml

@@ -23,5 +23,3 @@ metric_list:
     higher_is_better: true
 metadata:
   version: 2.0
-dataset_kwargs:
-  trust_remote_code: true

lm_eval/tasks/noreval/tatoeba/_tatoeba_yaml

@@ -2,8 +2,6 @@ dataset_path: Helsinki-NLP/tatoeba_mt
 training_split: validation
 test_split: test
 output_type: generate_until
-dataset_kwargs:
-  trust_remote_code: true
 metric_list:
   - metric: bleu
     higher_is_better: true

lm_eval/tasks/olaph/utils.py

@@ -12,7 +12,9 @@ try:
 
 except (ModuleNotFoundError, ImportError):
     raise ModuleNotFoundError(
-        "Please install evaluation metrics via pip install evaluate and pip install bert-score",
+        "Please install evaluation metrics via pip install evaluate bert-score "
+        "rouge_score>=0.1.2 nltk absl-py "
+        "git+https://github.com/google-research/bleurt.git"
     )
 except Exception as e:
     raise RuntimeError(

lm_eval/tasks/piqa/piqa.yaml

@@ -19,5 +19,3 @@ metric_list:
     higher_is_better: true
 metadata:
   version: 1.0
-dataset_kwargs:
-  trust_remote_code: true

lm_eval/tasks/portuguese_bench/flores_pt/_flores_common_yaml

@@ -23,5 +23,3 @@ metric_list:
     higher_is_better: true
 metadata:
   version: 1.0
-dataset_kwargs:
-  trust_remote_code: true