wisent 0.7.379__py3-none-any.whl → 0.7.901__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- wisent/__init__.py +1 -1
- wisent/core/activations/__init__.py +22 -6
- wisent/core/activations/activation_cache.py +393 -0
- wisent/core/activations/activations.py +22 -40
- wisent/core/activations/activations_collector.py +145 -373
- wisent/core/activations/classifier_inference_strategy.py +195 -0
- wisent/core/activations/core/atoms.py +8 -92
- wisent/core/activations/extraction_strategy.py +480 -0
- wisent/core/agent/diagnose/response_diagnostics.py +3 -3
- wisent/core/agent/diagnose.py +3 -3
- wisent/core/autonomous_agent.py +2 -2
- wisent/core/classifiers/classifiers/core/atoms.py +3 -2
- wisent/core/cli/__init__.py +2 -1
- wisent/core/cli/agent/apply_steering.py +25 -31
- wisent/core/cli/agent/evaluate_response.py +18 -20
- wisent/core/cli/agent/train_classifier.py +36 -26
- wisent/core/cli/check_linearity.py +35 -3
- wisent/core/cli/cluster_benchmarks.py +470 -0
- wisent/core/cli/create_steering_vector.py +19 -9
- wisent/core/cli/diagnose_vectors.py +7 -4
- wisent/core/cli/estimate_unified_goodness_time.py +6 -4
- wisent/core/cli/generate_pairs_from_task.py +9 -56
- wisent/core/cli/generate_vector_from_task.py +4 -0
- wisent/core/cli/geometry_search.py +137 -0
- wisent/core/cli/get_activations.py +13 -37
- wisent/core/cli/method_optimizer.py +860 -0
- wisent/core/cli/modify_weights.py +3 -2
- wisent/core/cli/optimize.py +44 -5
- wisent/core/cli/optimize_classification.py +5 -6
- wisent/core/cli/optimize_sample_size.py +9 -23
- wisent/core/cli/optimize_steering.py +433 -159
- wisent/core/cli/optimize_weights.py +67 -7
- wisent/core/cli/preview_pairs.py +203 -0
- wisent/core/cli/steering_method_trainer.py +8 -7
- wisent/core/cli/steering_search_space.py +20 -15
- wisent/core/cli/tasks.py +31 -117
- wisent/core/cli/train_unified_goodness.py +18 -19
- wisent/core/contrastive_pairs/diagnostics/control_vectors.py +1582 -177
- wisent/core/contrastive_pairs/diagnostics/linearity.py +70 -80
- wisent/core/contrastive_pairs/diagnostics/vector_quality.py +6 -5
- wisent/core/contrastive_pairs/huggingface_pairs/hf_extractor_manifest.py +5 -19
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/__init__.py +11 -5
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/agentic_search.py +37 -347
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/aider_polyglot.py +113 -136
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/apps.py +146 -32
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codeforces.py +2 -12
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue.py +2 -2
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/coding_benchmarks.py +124 -504
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/faithbench.py +40 -63
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/flames.py +46 -89
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/flores.py +15 -4
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/frames.py +36 -20
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/hallucinations_leaderboard.py +3 -45
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/humaneval.py +98 -57
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/livemathbench.py +42 -4
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/longform_writing.py +2 -112
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/math500.py +39 -4
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/medium_priority_benchmarks.py +475 -525
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/mercury.py +65 -42
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/olympiadbench.py +2 -12
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/planbench.py +78 -219
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/polymath.py +37 -4
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/recode.py +84 -69
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/refusalbench.py +168 -160
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/simpleqa.py +44 -25
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/tau_bench.py +3 -103
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/toolbench.py +3 -97
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/toolemu.py +48 -182
- wisent/core/contrastive_pairs/lm_eval_pairs/group_task_manifests/code_x_glue.py +8 -8
- wisent/core/contrastive_pairs/lm_eval_pairs/group_task_manifests/freebase.py +1 -1
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_extractor_manifest.py +11 -5
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_extractor_registry.py +19 -1
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/aclue.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/acp_bench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/acp_bench_hard.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/advanced.py +2 -4
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/aexams.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/afrimmlu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/afrixnli.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/agieval_aqua_rat.py +129 -0
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arabculture.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arabic.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arabic_exams.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arabic_leaderboard_complete.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arabic_leaderboard_light.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arabicmmlu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/aradice.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arc.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arc_challenge.py +1 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arc_easy.py +1 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/arithmetic.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/asdiv.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/babi.py +36 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/basque_bench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/bbq.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/belebele.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/benchmarks.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/bertaqa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/bhs.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/bhtc.py +3 -5
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/blimp.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/blimp_nl.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/boolq.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/c4.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/cabbq.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/careqa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/catalan_bench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/catalanqa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/catcola.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/cb.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/ceval.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/ceval_valid.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/chain.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/chartqa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/claim.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/click.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/cmmlu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/cnn.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/cocoteros.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/code_x_glue.py +11 -6
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/coedit.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/commonsense.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/commonsense_qa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/copa.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/copal_id.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/coqa.py +3 -4
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/csatqa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/cycle.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/darija_bench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/darijahellaswag.py +2 -6
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/darijammlu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/dbpedia.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/discrim_eval.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/doc.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/drop.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/epec.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/eq.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/eq_bench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/eq_bench_ca.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/eq_bench_es.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/esbbq.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/ethics.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/eus.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/eus_exams.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/eus_proficiency.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/eus_reading.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/eus_trivia.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/evalita_llm.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/financial.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/flan.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/french_bench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/galician_bench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/gaokao.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/glianorex.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/global_mmlu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/global_piqa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/gpt3.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/groundcocoa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/gsm8k.py +1 -1
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/haerae.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/headqa.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/hellaswag.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/hendrycks_ethics.py +5 -9
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/hendrycks_math.py +63 -16
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/histoires_morales.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/hrm8k.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/humaneval_infilling.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/icelandic_winogrande.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/inverse.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/inverse_scaling.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/ja.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/japanese_leaderboard.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/japanese_leaderboard_mc.py +1 -1
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/kmmlu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/kobest.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/kormedmcqa.py +5 -17
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/lambada_cloze.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/lambada_multilingual.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/law.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/leaderboard.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/lingoly.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/llama3.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/lm_syneval.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/logiqa.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/logiqa2.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/longbench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/longbenchv2.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/mastermind.py +2 -4
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/mbpp.py +47 -6
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/mc-taco.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/med_concepts_qa.py +2 -4
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/meddialog.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/medical.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/medmcqa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/medqa.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/mela.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/metabench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/minerva_math.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/mmlu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/mmlusr.py +3 -4
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/mrpc.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/multiblimp.py +2 -5
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/multirc.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/mutual.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/non.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/noreval.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/noreval_exact.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/noreval_gen_exact.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/noreval_mc.py +4 -8
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/noreval_mc_log_likelihoods.py +4 -8
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/nq_open.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/okapi_arc_multilingual.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/okapi_hellaswag_multilingual.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/okapi_mmlu_multilingual.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/okapi_truthfulqa_multilingual.py +2 -5
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/olaph.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/openbookqa.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/option.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/parafraseja.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/parafrases.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/paws.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/paws_x.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/pawsx.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/persona.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/phrases.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/pile.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/piqa.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/portuguese_bench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/prompt.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/prost.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/pubmedqa.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/qa4mre.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/qasper.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/qasper_bool.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/qnli.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/qnlieu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/qqp.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/race.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/random.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/record.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/reversed.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/rte.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/ruler.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/sciq.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/score.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/scrolls.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/scrolls_mc.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/self.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/sglue.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/sglue_rte.py +2 -1
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/siqa.py +4 -7
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/social_iqa.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/spanish_bench.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/storycloze.py +2 -6
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/summarization.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/super.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/super_glue.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/swag.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/swde.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/sycophancy.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/t0.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/teca.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/tinyarc.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/tinybenchmarks.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/tinygsm8k.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/tinyhellaswag.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/tinymmlu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/tinytruthfulqa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/tinywinogrande.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/tmmluplus.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/triviaqa.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/truthfulqa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/truthfulqa_mc1.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/truthfulqa_mc2.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/turblimp_core.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/turkishmmlu.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/turkishmmlu_mc.py +0 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/unscramble.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/vaxx.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/webqs.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/wic.py +3 -4
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/winogrande.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/wmdp.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/wnli.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/wsc.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/wsc273.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/xcopa.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/xlsum.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/xnli.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/xquad.py +2 -4
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/xstorycloze.py +2 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/xwinograd.py +2 -2
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/zhoblimp.py +1 -3
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_pairs_generation.py +173 -6
- wisent/core/data_loaders/loaders/lm_loader.py +12 -1
- wisent/core/evaluators/benchmark_specific/apps_evaluator.py +133 -0
- wisent/core/evaluators/benchmark_specific/coding/metrics/evaluator.py +6 -1
- wisent/core/evaluators/benchmark_specific/conala_evaluator.py +31 -168
- wisent/core/evaluators/custom/examples/humanization_coherent.py +89 -35
- wisent/core/evaluators/oracles/truthfulqa_gen_evaluator.py +2 -20
- wisent/core/evaluators/personalization/coherence.py +46 -0
- wisent/core/geometry_runner.py +995 -0
- wisent/core/geometry_search_space.py +237 -0
- wisent/core/hyperparameter_optimizer.py +14 -14
- wisent/core/lm_eval_harness_ground_truth.py +7 -11
- wisent/core/main.py +6 -0
- wisent/core/models/core/atoms.py +5 -3
- wisent/core/models/wisent_model.py +9 -8
- wisent/core/opti/methods/opti_weights.py +29 -2
- wisent/core/optuna/classifier/activation_generator.py +14 -12
- wisent/core/optuna/classifier/optuna_classifier_optimizer.py +2 -2
- wisent/core/optuna/steering/steering_optimization.py +14 -9
- wisent/core/parser_arguments/check_linearity_parser.py +12 -2
- wisent/core/parser_arguments/cluster_benchmarks_parser.py +31 -0
- wisent/core/parser_arguments/generate_vector_from_synthetic_parser.py +2 -2
- wisent/core/parser_arguments/generate_vector_from_task_parser.py +22 -2
- wisent/core/parser_arguments/geometry_search_parser.py +61 -0
- wisent/core/parser_arguments/main_parser.py +16 -0
- wisent/core/parser_arguments/optimize_steering_parser.py +117 -10
- wisent/core/parser_arguments/optimize_weights_parser.py +6 -0
- wisent/core/parser_arguments/tasks_parser.py +7 -19
- wisent/core/parser_arguments/train_unified_goodness_parser.py +2 -2
- wisent/core/steering.py +5 -3
- wisent/core/steering_methods/core/atoms.py +1 -2
- wisent/core/steering_methods/methods/caa.py +1 -1
- wisent/core/steering_methods/methods/hyperplane.py +75 -0
- wisent/core/steering_methods/methods/prism.py +1 -2
- wisent/core/steering_methods/methods/pulse.py +39 -8
- wisent/core/steering_methods/methods/titan.py +59 -14
- wisent/core/steering_methods/registry.py +52 -12
- wisent/core/steering_optimizer.py +15 -15
- wisent/core/synthetic/generators/nonsense_generator.py +30 -18
- wisent/core/trainers/steering_trainer.py +11 -20
- wisent/core/utils/device.py +27 -27
- wisent/core/utils/layer_combinations.py +70 -0
- wisent/examples/__init__.py +1 -0
- wisent/examples/scripts/__init__.py +1 -0
- wisent/examples/scripts/count_all_benchmarks.py +121 -0
- wisent/examples/scripts/discover_directions.py +469 -0
- wisent/examples/scripts/extract_benchmark_info.py +71 -0
- wisent/examples/scripts/generate_paper_data.py +384 -0
- wisent/examples/scripts/intervention_validation.py +626 -0
- wisent/examples/scripts/results/test_AraDiCE_ArabicMMLU_lev_evaluation.json +324 -0
- wisent/examples/scripts/results/test_AraDiCE_ArabicMMLU_lev_pairs.json +92 -0
- wisent/examples/scripts/results/test_aexams_IslamicStudies_evaluation.json +324 -0
- wisent/examples/scripts/results/test_aexams_IslamicStudies_pairs.json +92 -0
- wisent/examples/scripts/results/test_afrimgsm_pairs.json +92 -0
- wisent/examples/scripts/results/test_afrimmlu_evaluation.json +324 -0
- wisent/examples/scripts/results/test_afrimmlu_pairs.json +92 -0
- wisent/examples/scripts/search_all_short_names.py +31 -0
- wisent/examples/scripts/test_all_benchmarks.py +138 -0
- wisent/examples/scripts/test_all_benchmarks_new.py +28 -0
- wisent/examples/scripts/test_contrastive_pairs_all_supported.py +230 -0
- wisent/examples/scripts/test_nonsense_baseline.py +261 -0
- wisent/examples/scripts/test_one_benchmark.py +324 -0
- wisent/examples/scripts/test_one_coding_benchmark.py +293 -0
- wisent/examples/scripts/threshold_analysis.py +434 -0
- wisent/examples/scripts/visualization_gallery.py +582 -0
- wisent/parameters/lm_eval/broken_in_lm_eval.json +179 -2
- wisent/parameters/lm_eval/category_directions.json +137 -0
- wisent/parameters/lm_eval/repair_plan.json +282 -0
- wisent/parameters/lm_eval/track_progress_not_lm_eval_tasks.json +19 -70
- wisent/parameters/lm_eval/weak_contrastive_pairs.json +38 -0
- wisent/parameters/lm_eval/working_benchmarks.json +206 -0
- wisent/parameters/lm_eval/working_benchmarks_categorized.json +236 -0
- wisent/scripts/run_quality_metrics_sweep.sh +22 -27
- wisent/tests/test_aggregation_geometry.py +236 -0
- wisent/tests/test_detector_accuracy.py +163 -0
- wisent/tests/test_geometry_exhaustive.py +1202 -0
- wisent/tests/visualize_geometry.py +255 -61
- {wisent-0.7.379.dist-info → wisent-0.7.901.dist-info}/METADATA +1 -1
- {wisent-0.7.379.dist-info → wisent-0.7.901.dist-info}/RECORD +376 -974
- wisent/core/activations/prompt_construction_strategy.py +0 -47
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/browsecomp.py +0 -245
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text.py +0 -15
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_go.py +0 -64
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_java.py +0 -65
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_javascript.py +0 -65
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_php.py +0 -65
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_python.py +0 -65
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/codexglue_code_to_text_ruby.py +0 -65
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/freebase.py +0 -99
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/instruct_humaneval.py +0 -180
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/instructhumaneval.py +0 -129
- wisent/core/contrastive_pairs/huggingface_pairs/hf_task_extractors/mbpp.py +0 -142
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/agieval.py +0 -155
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/code2text.py +0 -161
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/codexglue.py +0 -107
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/livemathbench.py +0 -155
- wisent/core/contrastive_pairs/lm_eval_pairs/lm_task_extractors/polymath.py +0 -155
- wisent/examples/scripts/results/benchmark_descriptions.json +0 -1244
- wisent/examples/scripts/results/benchmark_evaluation_methods.json +0 -66
- wisent/examples/scripts/results/benchmark_evaluator_mapping.json +0 -2781
- wisent/examples/scripts/results/benchmark_evaluator_mapping_updated.json +0 -30536
- wisent/examples/scripts/results/benchmark_evaluators_clean.json +0 -469
- wisent/examples/scripts/results/benchmark_methods_summary.json +0 -260
- wisent/examples/scripts/results/benchmark_pair_creation_methods.json +0 -66
- wisent/examples/scripts/results/benchmark_pair_totals.json +0 -269
- wisent/examples/scripts/results/benchmark_tags.json +0 -917
- wisent/examples/scripts/results/benchmark_test_summary_nov4.json +0 -71
- wisent/examples/scripts/results/coding_benchmarks_test_code_status.json +0 -150
- wisent/examples/scripts/results/failing_benchmarks.json +0 -946
- wisent/examples/scripts/results/failing_benchmarks_list.json +0 -41
- wisent/examples/scripts/results/failing_benchmarks_test_results.json +0 -945
- wisent/examples/scripts/results/missing_benchmark_tags.json +0 -341
- wisent/examples/scripts/results/test_20_newsgroups_evaluation.json +0 -30
- wisent/examples/scripts/results/test_20_newsgroups_pairs.json +0 -8
- wisent/examples/scripts/results/test_AraDICE_evaluation.json +0 -51
- wisent/examples/scripts/results/test_AraDICE_pairs.json +0 -14
- wisent/examples/scripts/results/test_AraDiCE_boolq_egy/test_AraDiCE_boolq_egy_evaluation.json +0 -30
- wisent/examples/scripts/results/test_AraDiCE_boolq_egy/test_AraDiCE_boolq_egy_pairs.json +0 -8
- wisent/examples/scripts/results/test_ArabCulture_evaluation.json +0 -51
- wisent/examples/scripts/results/test_ArabCulture_pairs.json +0 -14
- wisent/examples/scripts/results/test_Tag_evaluation.json +0 -30
- wisent/examples/scripts/results/test_Tag_pairs.json +0 -8
- wisent/examples/scripts/results/test_aclue_evaluation.json +0 -51
- wisent/examples/scripts/results/test_aclue_pairs.json +0 -14
- wisent/examples/scripts/results/test_acp_bench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_acp_bench_hard_evaluation.json +0 -51
- wisent/examples/scripts/results/test_acp_bench_hard_pairs.json +0 -14
- wisent/examples/scripts/results/test_acp_bench_pairs.json +0 -14
- wisent/examples/scripts/results/test_advanced_ai_risk_evaluation.json +0 -51
- wisent/examples/scripts/results/test_advanced_ai_risk_pairs.json +0 -14
- wisent/examples/scripts/results/test_aexams_evaluation.json +0 -51
- wisent/examples/scripts/results/test_aexams_pairs.json +0 -14
- wisent/examples/scripts/results/test_afrimgsm_direct_amh_evaluation.json +0 -30
- wisent/examples/scripts/results/test_afrimgsm_direct_amh_pairs.json +0 -8
- wisent/examples/scripts/results/test_afrimmlu_direct_amh_evaluation.json +0 -30
- wisent/examples/scripts/results/test_afrimmlu_direct_amh_pairs.json +0 -8
- wisent/examples/scripts/results/test_afrixnli_en_direct_amh_evaluation.json +0 -30
- wisent/examples/scripts/results/test_afrixnli_en_direct_amh_pairs.json +0 -8
- wisent/examples/scripts/results/test_ag_news_evaluation.json +0 -30
- wisent/examples/scripts/results/test_ag_news_pairs.json +0 -8
- wisent/examples/scripts/results/test_agieval_evaluation.json +0 -51
- wisent/examples/scripts/results/test_agieval_pairs.json +0 -14
- wisent/examples/scripts/results/test_aime2024_evaluation.json +0 -30
- wisent/examples/scripts/results/test_aime2024_pairs.json +0 -8
- wisent/examples/scripts/results/test_aime2025_evaluation.json +0 -30
- wisent/examples/scripts/results/test_aime2025_pairs.json +0 -8
- wisent/examples/scripts/results/test_aime_evaluation.json +0 -30
- wisent/examples/scripts/results/test_aime_pairs.json +0 -8
- wisent/examples/scripts/results/test_anagrams1_evaluation.json +0 -30
- wisent/examples/scripts/results/test_anagrams1_pairs.json +0 -8
- wisent/examples/scripts/results/test_anagrams2_evaluation.json +0 -30
- wisent/examples/scripts/results/test_anagrams2_pairs.json +0 -8
- wisent/examples/scripts/results/test_anli_evaluation.json +0 -30
- wisent/examples/scripts/results/test_anli_pairs.json +0 -8
- wisent/examples/scripts/results/test_apps_evaluation.json +0 -30
- wisent/examples/scripts/results/test_apps_pairs.json +0 -8
- wisent/examples/scripts/results/test_arabic_exams_evaluation.json +0 -30
- wisent/examples/scripts/results/test_arabic_exams_pairs.json +0 -8
- wisent/examples/scripts/results/test_arabic_leaderboard_complete_evaluation.json +0 -51
- wisent/examples/scripts/results/test_arabic_leaderboard_complete_pairs.json +0 -14
- wisent/examples/scripts/results/test_arabic_leaderboard_light_evaluation.json +0 -51
- wisent/examples/scripts/results/test_arabic_leaderboard_light_pairs.json +0 -14
- wisent/examples/scripts/results/test_arabicmmlu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_arabicmmlu_pairs.json +0 -14
- wisent/examples/scripts/results/test_aradice/test_aradice_evaluation.json +0 -51
- wisent/examples/scripts/results/test_aradice/test_aradice_pairs.json +0 -14
- wisent/examples/scripts/results/test_aradice3/test_aradice_evaluation.json +0 -51
- wisent/examples/scripts/results/test_aradice3/test_aradice_pairs.json +0 -14
- wisent/examples/scripts/results/test_arc_ar_evaluation.json +0 -30
- wisent/examples/scripts/results/test_arc_ar_pairs.json +0 -8
- wisent/examples/scripts/results/test_arc_challenge_evaluation.json +0 -30
- wisent/examples/scripts/results/test_arc_challenge_pairs.json +0 -8
- wisent/examples/scripts/results/test_arc_easy_evaluation.json +0 -30
- wisent/examples/scripts/results/test_arc_easy_pairs.json +0 -8
- wisent/examples/scripts/results/test_argument_topic_evaluation.json +0 -30
- wisent/examples/scripts/results/test_argument_topic_pairs.json +0 -8
- wisent/examples/scripts/results/test_arithmetic_evaluation.json +0 -51
- wisent/examples/scripts/results/test_arithmetic_pairs.json +0 -14
- wisent/examples/scripts/results/test_asdiv_evaluation.json +0 -30
- wisent/examples/scripts/results/test_asdiv_pairs.json +0 -8
- wisent/examples/scripts/results/test_assin_entailment_evaluation.json +0 -30
- wisent/examples/scripts/results/test_assin_entailment_pairs.json +0 -8
- wisent/examples/scripts/results/test_atis_evaluation.json +0 -30
- wisent/examples/scripts/results/test_atis_pairs.json +0 -8
- wisent/examples/scripts/results/test_babi_evaluation.json +0 -30
- wisent/examples/scripts/results/test_babi_pairs.json +0 -8
- wisent/examples/scripts/results/test_babilong_evaluation.json +0 -30
- wisent/examples/scripts/results/test_babilong_pairs.json +0 -8
- wisent/examples/scripts/results/test_bangla_mmlu_evaluation.json +0 -30
- wisent/examples/scripts/results/test_bangla_mmlu_pairs.json +0 -8
- wisent/examples/scripts/results/test_banking77_evaluation.json +0 -30
- wisent/examples/scripts/results/test_banking77_pairs.json +0 -8
- wisent/examples/scripts/results/test_basque/test_basque-glue_pairs.json +0 -14
- wisent/examples/scripts/results/test_basque-glue_evaluation.json +0 -51
- wisent/examples/scripts/results/test_basque-glue_pairs.json +0 -14
- wisent/examples/scripts/results/test_basque2/test_basque-glue_evaluation.json +0 -51
- wisent/examples/scripts/results/test_basque2/test_basque-glue_pairs.json +0 -14
- wisent/examples/scripts/results/test_basque_bench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_basque_bench_pairs.json +0 -14
- wisent/examples/scripts/results/test_basque_glue/test_basque-glue_evaluation.json +0 -51
- wisent/examples/scripts/results/test_basque_glue/test_basque-glue_pairs.json +0 -14
- wisent/examples/scripts/results/test_basqueglue_evaluation.json +0 -51
- wisent/examples/scripts/results/test_basqueglue_pairs.json +0 -14
- wisent/examples/scripts/results/test_bbh_evaluation.json +0 -51
- wisent/examples/scripts/results/test_bbh_pairs.json +0 -14
- wisent/examples/scripts/results/test_bbq_evaluation.json +0 -30
- wisent/examples/scripts/results/test_bbq_pairs.json +0 -8
- wisent/examples/scripts/results/test_bec2016eu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_bec2016eu_pairs.json +0 -14
- wisent/examples/scripts/results/test_belebele_evaluation.json +0 -51
- wisent/examples/scripts/results/test_belebele_pairs.json +0 -14
- wisent/examples/scripts/results/test_benchmarks_evaluation.json +0 -51
- wisent/examples/scripts/results/test_benchmarks_pairs.json +0 -14
- wisent/examples/scripts/results/test_bertaqa_evaluation.json +0 -51
- wisent/examples/scripts/results/test_bertaqa_pairs.json +0 -14
- wisent/examples/scripts/results/test_bhtc_v2_evaluation.json +0 -30
- wisent/examples/scripts/results/test_bhtc_v2_pairs.json +0 -8
- wisent/examples/scripts/results/test_bigbench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_bigbench_pairs.json +0 -14
- wisent/examples/scripts/results/test_blimp_evaluation.json +0 -51
- wisent/examples/scripts/results/test_blimp_pairs.json +0 -14
- wisent/examples/scripts/results/test_boolq/test_boolq_evaluation.json +0 -30
- wisent/examples/scripts/results/test_boolq/test_boolq_pairs.json +0 -8
- wisent/examples/scripts/results/test_boolq-seq2seq_evaluation.json +0 -30
- wisent/examples/scripts/results/test_boolq-seq2seq_pairs.json +0 -8
- wisent/examples/scripts/results/test_boolq_evaluation.json +0 -30
- wisent/examples/scripts/results/test_boolq_pairs.json +0 -8
- wisent/examples/scripts/results/test_c4_evaluation.json +0 -30
- wisent/examples/scripts/results/test_c4_pairs.json +0 -8
- wisent/examples/scripts/results/test_cabreu_evaluation.json +0 -30
- wisent/examples/scripts/results/test_cabreu_pairs.json +0 -8
- wisent/examples/scripts/results/test_careqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_careqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_catalan_bench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_catalan_bench_pairs.json +0 -14
- wisent/examples/scripts/results/test_catalanqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_catalanqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_catcola_evaluation.json +0 -30
- wisent/examples/scripts/results/test_catcola_pairs.json +0 -8
- wisent/examples/scripts/results/test_cb_evaluation.json +0 -30
- wisent/examples/scripts/results/test_cb_pairs.json +0 -8
- wisent/examples/scripts/results/test_ceval/test_ceval_evaluation.json +0 -51
- wisent/examples/scripts/results/test_ceval/test_ceval_pairs.json +0 -14
- wisent/examples/scripts/results/test_ceval_accountant/test_ceval-valid_accountant_evaluation.json +0 -30
- wisent/examples/scripts/results/test_ceval_accountant/test_ceval-valid_accountant_pairs.json +0 -8
- wisent/examples/scripts/results/test_ceval_evaluation.json +0 -51
- wisent/examples/scripts/results/test_ceval_pairs.json +0 -14
- wisent/examples/scripts/results/test_ceval_valid/test_ceval_valid_evaluation.json +0 -51
- wisent/examples/scripts/results/test_ceval_valid/test_ceval_valid_pairs.json +0 -14
- wisent/examples/scripts/results/test_chain_of_thought_evaluation.json +0 -51
- wisent/examples/scripts/results/test_chain_of_thought_pairs.json +0 -14
- wisent/examples/scripts/results/test_chartqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_chartqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_claim_stance_topic_evaluation.json +0 -30
- wisent/examples/scripts/results/test_claim_stance_topic_pairs.json +0 -8
- wisent/examples/scripts/results/test_cmmlu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_cmmlu_pairs.json +0 -14
- wisent/examples/scripts/results/test_cnn_dailymail_evaluation.json +0 -30
- wisent/examples/scripts/results/test_cnn_dailymail_pairs.json +0 -8
- wisent/examples/scripts/results/test_cocoteros_es_evaluation.json +0 -30
- wisent/examples/scripts/results/test_cocoteros_es_pairs.json +0 -8
- wisent/examples/scripts/results/test_codexglue_code_to_text_go_evaluation.json +0 -30
- wisent/examples/scripts/results/test_codexglue_code_to_text_go_pairs.json +0 -8
- wisent/examples/scripts/results/test_codexglue_code_to_text_java_evaluation.json +0 -30
- wisent/examples/scripts/results/test_codexglue_code_to_text_java_pairs.json +0 -8
- wisent/examples/scripts/results/test_codexglue_code_to_text_javascript_evaluation.json +0 -30
- wisent/examples/scripts/results/test_codexglue_code_to_text_javascript_pairs.json +0 -8
- wisent/examples/scripts/results/test_codexglue_code_to_text_php_evaluation.json +0 -30
- wisent/examples/scripts/results/test_codexglue_code_to_text_php_pairs.json +0 -8
- wisent/examples/scripts/results/test_codexglue_code_to_text_python_evaluation.json +0 -30
- wisent/examples/scripts/results/test_codexglue_code_to_text_python_pairs.json +0 -8
- wisent/examples/scripts/results/test_codexglue_code_to_text_ruby_evaluation.json +0 -30
- wisent/examples/scripts/results/test_codexglue_code_to_text_ruby_pairs.json +0 -8
- wisent/examples/scripts/results/test_coedit_gec_evaluation.json +0 -30
- wisent/examples/scripts/results/test_coedit_gec_pairs.json +0 -8
- wisent/examples/scripts/results/test_cola_evaluation.json +0 -30
- wisent/examples/scripts/results/test_cola_pairs.json +0 -8
- wisent/examples/scripts/results/test_commonsense_qa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_commonsense_qa_pairs.json +0 -8
- wisent/examples/scripts/results/test_conala_evaluation.json +0 -30
- wisent/examples/scripts/results/test_conala_pairs.json +0 -8
- wisent/examples/scripts/results/test_concode_evaluation.json +0 -30
- wisent/examples/scripts/results/test_concode_pairs.json +0 -8
- wisent/examples/scripts/results/test_copa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_copa_pairs.json +0 -8
- wisent/examples/scripts/results/test_copal_id_evaluation.json +0 -30
- wisent/examples/scripts/results/test_copal_id_pairs.json +0 -8
- wisent/examples/scripts/results/test_coqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_coqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_coqcat_evaluation.json +0 -30
- wisent/examples/scripts/results/test_coqcat_pairs.json +0 -8
- wisent/examples/scripts/results/test_crows_pairs_evaluation.json +0 -51
- wisent/examples/scripts/results/test_crows_pairs_pairs.json +0 -14
- wisent/examples/scripts/results/test_csatqa_evaluation.json +0 -51
- wisent/examples/scripts/results/test_csatqa_pairs.json +0 -14
- wisent/examples/scripts/results/test_cycle_letters_evaluation.json +0 -30
- wisent/examples/scripts/results/test_cycle_letters_pairs.json +0 -8
- wisent/examples/scripts/results/test_darija_bench/test_darija_bench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_darija_bench/test_darija_bench_pairs.json +0 -14
- wisent/examples/scripts/results/test_darija_bench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_darija_bench_pairs.json +0 -14
- wisent/examples/scripts/results/test_darijahellaswag_evaluation.json +0 -30
- wisent/examples/scripts/results/test_darijahellaswag_pairs.json +0 -8
- wisent/examples/scripts/results/test_darijammlu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_darijammlu_pairs.json +0 -14
- wisent/examples/scripts/results/test_dbpedia_14_evaluation.json +0 -30
- wisent/examples/scripts/results/test_dbpedia_14_pairs.json +0 -8
- wisent/examples/scripts/results/test_drop_evaluation.json +0 -30
- wisent/examples/scripts/results/test_drop_pairs.json +0 -8
- wisent/examples/scripts/results/test_ds1000_evaluation.json +0 -30
- wisent/examples/scripts/results/test_ds1000_pairs.json +0 -8
- wisent/examples/scripts/results/test_egyhellaswag_evaluation.json +0 -30
- wisent/examples/scripts/results/test_egyhellaswag_pairs.json +0 -8
- wisent/examples/scripts/results/test_egymmlu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_egymmlu_pairs.json +0 -14
- wisent/examples/scripts/results/test_epec_koref_bin_evaluation.json +0 -30
- wisent/examples/scripts/results/test_epec_koref_bin_pairs.json +0 -8
- wisent/examples/scripts/results/test_eq_bench_evaluation.json +0 -30
- wisent/examples/scripts/results/test_eq_bench_pairs.json +0 -8
- wisent/examples/scripts/results/test_escola_evaluation.json +0 -30
- wisent/examples/scripts/results/test_escola_pairs.json +0 -8
- wisent/examples/scripts/results/test_ethics_cm_evaluation.json +0 -30
- wisent/examples/scripts/results/test_ethics_cm_pairs.json +0 -8
- wisent/examples/scripts/results/test_ethos_binary_evaluation.json +0 -30
- wisent/examples/scripts/results/test_ethos_binary_pairs.json +0 -8
- wisent/examples/scripts/results/test_eus_exams/test_eus_exams_evaluation.json +0 -51
- wisent/examples/scripts/results/test_eus_exams/test_eus_exams_pairs.json +0 -14
- wisent/examples/scripts/results/test_eus_exams_es_evaluation.json +0 -51
- wisent/examples/scripts/results/test_eus_exams_es_pairs.json +0 -14
- wisent/examples/scripts/results/test_eus_exams_evaluation.json +0 -51
- wisent/examples/scripts/results/test_eus_exams_pairs.json +0 -14
- wisent/examples/scripts/results/test_eus_proficiency_evaluation.json +0 -30
- wisent/examples/scripts/results/test_eus_proficiency_pairs.json +0 -8
- wisent/examples/scripts/results/test_eus_reading_evaluation.json +0 -30
- wisent/examples/scripts/results/test_eus_reading_pairs.json +0 -8
- wisent/examples/scripts/results/test_eus_trivia_evaluation.json +0 -30
- wisent/examples/scripts/results/test_eus_trivia_pairs.json +0 -8
- wisent/examples/scripts/results/test_evalita-mp_evaluation.json +0 -51
- wisent/examples/scripts/results/test_evalita-mp_pairs.json +0 -14
- wisent/examples/scripts/results/test_evalita-sp_sum_task_fp-small_p1_evaluation.json +0 -30
- wisent/examples/scripts/results/test_evalita-sp_sum_task_fp-small_p1_pairs.json +0 -8
- wisent/examples/scripts/results/test_evalita_LLM_evaluation.json +0 -51
- wisent/examples/scripts/results/test_evalita_LLM_pairs.json +0 -14
- wisent/examples/scripts/results/test_evalita_llm/test_evalita_llm_evaluation.json +0 -51
- wisent/examples/scripts/results/test_evalita_llm/test_evalita_llm_pairs.json +0 -14
- wisent/examples/scripts/results/test_evalita_mp/test_evalita-mp_te_prompt-1_evaluation.json +0 -30
- wisent/examples/scripts/results/test_evalita_mp/test_evalita-mp_te_prompt-1_pairs.json +0 -8
- wisent/examples/scripts/results/test_evalita_mp2/test_evalita_mp_evaluation.json +0 -51
- wisent/examples/scripts/results/test_evalita_mp2/test_evalita_mp_pairs.json +0 -14
- wisent/examples/scripts/results/test_evalita_sp2/test_evalita-sp_sum_task_fp-small_p1_evaluation.json +0 -30
- wisent/examples/scripts/results/test_evalita_sp2/test_evalita-sp_sum_task_fp-small_p1_pairs.json +0 -8
- wisent/examples/scripts/results/test_fda_evaluation.json +0 -30
- wisent/examples/scripts/results/test_fda_pairs.json +0 -8
- wisent/examples/scripts/results/test_financial_tweets_evaluation.json +0 -30
- wisent/examples/scripts/results/test_financial_tweets_pairs.json +0 -8
- wisent/examples/scripts/results/test_fld/test_fld_evaluation.json +0 -30
- wisent/examples/scripts/results/test_fld/test_fld_pairs.json +0 -8
- wisent/examples/scripts/results/test_fld_evaluation.json +0 -30
- wisent/examples/scripts/results/test_fld_fixed/test_fld_evaluation.json +0 -30
- wisent/examples/scripts/results/test_fld_fixed/test_fld_pairs.json +0 -8
- wisent/examples/scripts/results/test_fld_pairs.json +0 -8
- wisent/examples/scripts/results/test_flores_evaluation.json +0 -51
- wisent/examples/scripts/results/test_flores_pairs.json +0 -14
- wisent/examples/scripts/results/test_freebase_evaluation.json +0 -30
- wisent/examples/scripts/results/test_freebase_pairs.json +0 -8
- wisent/examples/scripts/results/test_french_bench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_french_bench_pairs.json +0 -14
- wisent/examples/scripts/results/test_galcola_evaluation.json +0 -30
- wisent/examples/scripts/results/test_galcola_pairs.json +0 -8
- wisent/examples/scripts/results/test_galician_bench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_galician_bench_pairs.json +0 -14
- wisent/examples/scripts/results/test_glianorex_evaluation.json +0 -30
- wisent/examples/scripts/results/test_glianorex_pairs.json +0 -8
- wisent/examples/scripts/results/test_global_mmlu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_global_mmlu_pairs.json +0 -14
- wisent/examples/scripts/results/test_glue_evaluation.json +0 -51
- wisent/examples/scripts/results/test_glue_pairs.json +0 -14
- wisent/examples/scripts/results/test_gpqa_evaluation.json +0 -51
- wisent/examples/scripts/results/test_gpqa_pairs.json +0 -14
- wisent/examples/scripts/results/test_gpt3_translation_benchmarks_evaluation.json +0 -51
- wisent/examples/scripts/results/test_gpt3_translation_benchmarks_pairs.json +0 -14
- wisent/examples/scripts/results/test_groundcocoa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_groundcocoa_pairs.json +0 -8
- wisent/examples/scripts/results/test_gsm8k_evaluation.json +0 -30
- wisent/examples/scripts/results/test_gsm8k_pairs.json +0 -8
- wisent/examples/scripts/results/test_haerae_evaluation.json +0 -51
- wisent/examples/scripts/results/test_haerae_pairs.json +0 -14
- wisent/examples/scripts/results/test_headqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_headqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_hellaswag_evaluation.json +0 -30
- wisent/examples/scripts/results/test_hellaswag_pairs.json +0 -8
- wisent/examples/scripts/results/test_hendrycks_ethics_evaluation.json +0 -51
- wisent/examples/scripts/results/test_hendrycks_ethics_pairs.json +0 -14
- wisent/examples/scripts/results/test_hendrycks_math_evaluation.json +0 -51
- wisent/examples/scripts/results/test_hendrycks_math_pairs.json +0 -14
- wisent/examples/scripts/results/test_histoires_morales_evaluation.json +0 -30
- wisent/examples/scripts/results/test_histoires_morales_pairs.json +0 -8
- wisent/examples/scripts/results/test_hmmt_evaluation.json +0 -30
- wisent/examples/scripts/results/test_hmmt_feb_2025_evaluation.json +0 -30
- wisent/examples/scripts/results/test_hmmt_feb_2025_pairs.json +0 -8
- wisent/examples/scripts/results/test_hmmt_pairs.json +0 -8
- wisent/examples/scripts/results/test_hrm8k_evaluation.json +0 -51
- wisent/examples/scripts/results/test_hrm8k_pairs.json +0 -14
- wisent/examples/scripts/results/test_humaneval_evaluation.json +0 -30
- wisent/examples/scripts/results/test_humaneval_pairs.json +0 -8
- wisent/examples/scripts/results/test_humaneval_plus_evaluation.json +0 -30
- wisent/examples/scripts/results/test_humaneval_plus_pairs.json +0 -8
- wisent/examples/scripts/results/test_ifeval_evaluation.json +0 -30
- wisent/examples/scripts/results/test_ifeval_pairs.json +0 -8
- wisent/examples/scripts/results/test_instruct_humaneval/test_instruct_humaneval_evaluation.json +0 -30
- wisent/examples/scripts/results/test_instruct_humaneval/test_instruct_humaneval_pairs.json +0 -8
- wisent/examples/scripts/results/test_instruct_humaneval_evaluation.json +0 -30
- wisent/examples/scripts/results/test_instruct_humaneval_pairs.json +0 -8
- wisent/examples/scripts/results/test_inverse_scaling_evaluation.json +0 -51
- wisent/examples/scripts/results/test_inverse_scaling_hindsight_neglect_10shot_evaluation.json +0 -30
- wisent/examples/scripts/results/test_inverse_scaling_hindsight_neglect_10shot_pairs.json +0 -8
- wisent/examples/scripts/results/test_inverse_scaling_mc/test_inverse_scaling_mc_evaluation.json +0 -51
- wisent/examples/scripts/results/test_inverse_scaling_mc/test_inverse_scaling_mc_pairs.json +0 -14
- wisent/examples/scripts/results/test_inverse_scaling_pairs.json +0 -14
- wisent/examples/scripts/results/test_iwslt2017-ar-en_evaluation.json +0 -30
- wisent/examples/scripts/results/test_iwslt2017-ar-en_pairs.json +0 -8
- wisent/examples/scripts/results/test_iwslt2017-en-ar_evaluation.json +0 -30
- wisent/examples/scripts/results/test_iwslt2017-en-ar_pairs.json +0 -8
- wisent/examples/scripts/results/test_iwslt2017_ar_en/test_iwslt2017-ar-en_evaluation.json +0 -30
- wisent/examples/scripts/results/test_iwslt2017_ar_en/test_iwslt2017-ar-en_pairs.json +0 -8
- wisent/examples/scripts/results/test_iwslt2017_en_ar/test_iwslt2017-en-ar_evaluation.json +0 -30
- wisent/examples/scripts/results/test_iwslt2017_en_ar/test_iwslt2017-en-ar_pairs.json +0 -8
- wisent/examples/scripts/results/test_iwslt2017_group/test_iwslt2017_evaluation.json +0 -30
- wisent/examples/scripts/results/test_iwslt2017_group/test_iwslt2017_pairs.json +0 -8
- wisent/examples/scripts/results/test_japanese_leaderboard_evaluation.json +0 -51
- wisent/examples/scripts/results/test_japanese_leaderboard_pairs.json +0 -14
- wisent/examples/scripts/results/test_jsonschema_bench/test_jsonschema_bench_evaluation.json +0 -30
- wisent/examples/scripts/results/test_jsonschema_bench/test_jsonschema_bench_pairs.json +0 -8
- wisent/examples/scripts/results/test_jsonschema_bench_evaluation.json +0 -30
- wisent/examples/scripts/results/test_jsonschema_bench_final/test_jsonschema_bench_evaluation.json +0 -30
- wisent/examples/scripts/results/test_jsonschema_bench_final/test_jsonschema_bench_pairs.json +0 -8
- wisent/examples/scripts/results/test_jsonschema_bench_pairs.json +0 -8
- wisent/examples/scripts/results/test_kbl_evaluation.json +0 -51
- wisent/examples/scripts/results/test_kbl_fixed/test_kbl_evaluation.json +0 -51
- wisent/examples/scripts/results/test_kbl_fixed/test_kbl_pairs.json +0 -14
- wisent/examples/scripts/results/test_kbl_pairs.json +0 -14
- wisent/examples/scripts/results/test_kmmlu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_kmmlu_pairs.json +0 -14
- wisent/examples/scripts/results/test_kobest_evaluation.json +0 -51
- wisent/examples/scripts/results/test_kobest_pairs.json +0 -14
- wisent/examples/scripts/results/test_kormedmcqa/test_kormedmcqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_kormedmcqa/test_kormedmcqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_kormedmcqa_dentist/test_kormedmcqa_dentist_evaluation.json +0 -30
- wisent/examples/scripts/results/test_kormedmcqa_dentist/test_kormedmcqa_dentist_pairs.json +0 -8
- wisent/examples/scripts/results/test_kormedmcqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_kormedmcqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_lambada_cloze_evaluation.json +0 -30
- wisent/examples/scripts/results/test_lambada_cloze_pairs.json +0 -8
- wisent/examples/scripts/results/test_lambada_evaluation.json +0 -30
- wisent/examples/scripts/results/test_lambada_final/test_lambada_openai_mt_stablelm_en_evaluation.json +0 -30
- wisent/examples/scripts/results/test_lambada_final/test_lambada_openai_mt_stablelm_en_pairs.json +0 -8
- wisent/examples/scripts/results/test_lambada_multilingual/test_lambada_multilingual_evaluation.json +0 -51
- wisent/examples/scripts/results/test_lambada_multilingual/test_lambada_multilingual_pairs.json +0 -14
- wisent/examples/scripts/results/test_lambada_multilingual_evaluation.json +0 -51
- wisent/examples/scripts/results/test_lambada_multilingual_pairs.json +0 -14
- wisent/examples/scripts/results/test_lambada_multilingual_stablelm_evaluation.json +0 -51
- wisent/examples/scripts/results/test_lambada_multilingual_stablelm_pairs.json +0 -14
- wisent/examples/scripts/results/test_lambada_openai_evaluation.json +0 -30
- wisent/examples/scripts/results/test_lambada_openai_pairs.json +0 -8
- wisent/examples/scripts/results/test_lambada_pairs.json +0 -8
- wisent/examples/scripts/results/test_lambada_stablelm_en_fixed/test_lambada_openai_mt_stablelm_en_evaluation.json +0 -30
- wisent/examples/scripts/results/test_lambada_stablelm_en_fixed/test_lambada_openai_mt_stablelm_en_pairs.json +0 -8
- wisent/examples/scripts/results/test_lambada_stablelm_fixed/test_lambada_openai_mt_stablelm_en_evaluation.json +0 -30
- wisent/examples/scripts/results/test_lambada_stablelm_fixed/test_lambada_openai_mt_stablelm_en_pairs.json +0 -8
- wisent/examples/scripts/results/test_lambada_standard_evaluation.json +0 -30
- wisent/examples/scripts/results/test_lambada_standard_pairs.json +0 -8
- wisent/examples/scripts/results/test_leaderboard_evaluation.json +0 -51
- wisent/examples/scripts/results/test_leaderboard_pairs.json +0 -14
- wisent/examples/scripts/results/test_libra/test_libra_evaluation.json +0 -51
- wisent/examples/scripts/results/test_libra/test_libra_pairs.json +0 -14
- wisent/examples/scripts/results/test_libra_evaluation.json +0 -51
- wisent/examples/scripts/results/test_libra_pairs.json +0 -14
- wisent/examples/scripts/results/test_lingoly_evaluation.json +0 -30
- wisent/examples/scripts/results/test_lingoly_pairs.json +0 -8
- wisent/examples/scripts/results/test_livecodebench_evaluation.json +0 -30
- wisent/examples/scripts/results/test_livecodebench_pairs.json +0 -8
- wisent/examples/scripts/results/test_livemathbench_cnmo_en_evaluation.json +0 -30
- wisent/examples/scripts/results/test_livemathbench_cnmo_en_pairs.json +0 -8
- wisent/examples/scripts/results/test_livemathbench_cnmo_zh_evaluation.json +0 -30
- wisent/examples/scripts/results/test_livemathbench_cnmo_zh_pairs.json +0 -8
- wisent/examples/scripts/results/test_llama_evaluation.json +0 -30
- wisent/examples/scripts/results/test_llama_pairs.json +0 -8
- wisent/examples/scripts/results/test_logiqa2_evaluation.json +0 -30
- wisent/examples/scripts/results/test_logiqa2_pairs.json +0 -8
- wisent/examples/scripts/results/test_logiqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_logiqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_m_mmlu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_m_mmlu_pairs.json +0 -14
- wisent/examples/scripts/results/test_mastermind/test_mastermind_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mastermind/test_mastermind_pairs.json +0 -14
- wisent/examples/scripts/results/test_mastermind_24_easy/test_mastermind_24_easy_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mastermind_24_easy/test_mastermind_24_easy_pairs.json +0 -8
- wisent/examples/scripts/results/test_mastermind_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mastermind_pairs.json +0 -14
- wisent/examples/scripts/results/test_math500_evaluation.json +0 -30
- wisent/examples/scripts/results/test_math500_pairs.json +0 -8
- wisent/examples/scripts/results/test_math_evaluation.json +0 -30
- wisent/examples/scripts/results/test_math_pairs.json +0 -8
- wisent/examples/scripts/results/test_mathqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mathqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_mbpp_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mbpp_pairs.json +0 -8
- wisent/examples/scripts/results/test_mbpp_plus_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mbpp_plus_pairs.json +0 -8
- wisent/examples/scripts/results/test_mc_taco_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mc_taco_pairs.json +0 -8
- wisent/examples/scripts/results/test_med_concepts_qa/test_med_concepts_qa_evaluation.json +0 -51
- wisent/examples/scripts/results/test_med_concepts_qa/test_med_concepts_qa_pairs.json +0 -14
- wisent/examples/scripts/results/test_med_concepts_qa_atc_easy/test_med_concepts_qa_atc_easy_evaluation.json +0 -30
- wisent/examples/scripts/results/test_med_concepts_qa_atc_easy/test_med_concepts_qa_atc_easy_pairs.json +0 -8
- wisent/examples/scripts/results/test_med_concepts_qa_evaluation.json +0 -51
- wisent/examples/scripts/results/test_med_concepts_qa_pairs.json +0 -14
- wisent/examples/scripts/results/test_meddialog_evaluation.json +0 -30
- wisent/examples/scripts/results/test_meddialog_pairs.json +0 -8
- wisent/examples/scripts/results/test_meddialog_raw_perplexity/test_meddialog_raw_perplexity_evaluation.json +0 -30
- wisent/examples/scripts/results/test_meddialog_raw_perplexity/test_meddialog_raw_perplexity_pairs.json +0 -8
- wisent/examples/scripts/results/test_mediqa_qa2019_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mediqa_qa2019_pairs.json +0 -8
- wisent/examples/scripts/results/test_medmcqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_medmcqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_medqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_medqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_medtext_evaluation.json +0 -30
- wisent/examples/scripts/results/test_medtext_pairs.json +0 -8
- wisent/examples/scripts/results/test_mela_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mela_pairs.json +0 -14
- wisent/examples/scripts/results/test_meqsum_evaluation.json +0 -30
- wisent/examples/scripts/results/test_meqsum_pairs.json +0 -8
- wisent/examples/scripts/results/test_mercury_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mercury_pairs.json +0 -8
- wisent/examples/scripts/results/test_metabench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_metabench_pairs.json +0 -14
- wisent/examples/scripts/results/test_mgsm_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mgsm_pairs.json +0 -14
- wisent/examples/scripts/results/test_mimic_repsum_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mimic_repsum_pairs.json +0 -8
- wisent/examples/scripts/results/test_minerva_math_evaluation.json +0 -51
- wisent/examples/scripts/results/test_minerva_math_pairs.json +0 -14
- wisent/examples/scripts/results/test_mlqa_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mlqa_pairs.json +0 -14
- wisent/examples/scripts/results/test_mmlu-pro-plus_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mmlu-pro-plus_pairs.json +0 -14
- wisent/examples/scripts/results/test_mmlu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mmlu_pairs.json +0 -14
- wisent/examples/scripts/results/test_mmlu_pro_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mmlu_pro_pairs.json +0 -14
- wisent/examples/scripts/results/test_mmlu_prox_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mmlu_prox_pairs.json +0 -14
- wisent/examples/scripts/results/test_mmlusr_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mmlusr_pairs.json +0 -8
- wisent/examples/scripts/results/test_mmmu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_mmmu_pairs.json +0 -14
- wisent/examples/scripts/results/test_mnli_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mnli_pairs.json +0 -8
- wisent/examples/scripts/results/test_model_written_evals_evaluation.json +0 -51
- wisent/examples/scripts/results/test_model_written_evals_pairs.json +0 -14
- wisent/examples/scripts/results/test_moral_stories_evaluation.json +0 -30
- wisent/examples/scripts/results/test_moral_stories_pairs.json +0 -8
- wisent/examples/scripts/results/test_mts_dialog_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mts_dialog_pairs.json +0 -8
- wisent/examples/scripts/results/test_multiblimp_evaluation.json +0 -51
- wisent/examples/scripts/results/test_multiblimp_pairs.json +0 -14
- wisent/examples/scripts/results/test_multimedqa_evaluation.json +0 -51
- wisent/examples/scripts/results/test_multimedqa_pairs.json +0 -14
- wisent/examples/scripts/results/test_multipl_e_evaluation.json +0 -30
- wisent/examples/scripts/results/test_multipl_e_pairs.json +0 -8
- wisent/examples/scripts/results/test_mutual_evaluation.json +0 -30
- wisent/examples/scripts/results/test_mutual_pairs.json +0 -8
- wisent/examples/scripts/results/test_non_greedy_robustness_agieval_aqua_rat_evaluation.json +0 -30
- wisent/examples/scripts/results/test_non_greedy_robustness_agieval_aqua_rat_pairs.json +0 -8
- wisent/examples/scripts/results/test_noreval_evaluation.json +0 -51
- wisent/examples/scripts/results/test_noreval_pairs.json +0 -14
- wisent/examples/scripts/results/test_noticia_evaluation.json +0 -30
- wisent/examples/scripts/results/test_noticia_pairs.json +0 -8
- wisent/examples/scripts/results/test_nq_open_evaluation.json +0 -30
- wisent/examples/scripts/results/test_nq_open_pairs.json +0 -8
- wisent/examples/scripts/results/test_olaph_evaluation.json +0 -30
- wisent/examples/scripts/results/test_olaph_pairs.json +0 -8
- wisent/examples/scripts/results/test_openbookqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_openbookqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_openllm_evaluation.json +0 -51
- wisent/examples/scripts/results/test_openllm_pairs.json +0 -14
- wisent/examples/scripts/results/test_option_order_robustness_agieval_aqua_rat_evaluation.json +0 -30
- wisent/examples/scripts/results/test_option_order_robustness_agieval_aqua_rat_pairs.json +0 -8
- wisent/examples/scripts/results/test_paloma_evaluation.json +0 -51
- wisent/examples/scripts/results/test_paloma_pairs.json +0 -14
- wisent/examples/scripts/results/test_passkey/test_passkey_evaluation.json +0 -30
- wisent/examples/scripts/results/test_passkey/test_passkey_pairs.json +0 -8
- wisent/examples/scripts/results/test_paws-x_evaluation.json +0 -51
- wisent/examples/scripts/results/test_paws-x_pairs.json +0 -14
- wisent/examples/scripts/results/test_paws_en/test_paws_en_evaluation.json +0 -30
- wisent/examples/scripts/results/test_paws_en/test_paws_en_pairs.json +0 -8
- wisent/examples/scripts/results/test_penn_treebank_evaluation.json +0 -30
- wisent/examples/scripts/results/test_penn_treebank_pairs.json +0 -8
- wisent/examples/scripts/results/test_pile_10k/test_pile_10k_evaluation.json +0 -30
- wisent/examples/scripts/results/test_pile_10k/test_pile_10k_pairs.json +0 -8
- wisent/examples/scripts/results/test_piqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_piqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_polemo2_evaluation.json +0 -30
- wisent/examples/scripts/results/test_polemo2_pairs.json +0 -8
- wisent/examples/scripts/results/test_polymath_en_high_evaluation.json +0 -30
- wisent/examples/scripts/results/test_polymath_en_high_pairs.json +0 -8
- wisent/examples/scripts/results/test_polymath_en_medium_evaluation.json +0 -30
- wisent/examples/scripts/results/test_polymath_en_medium_pairs.json +0 -8
- wisent/examples/scripts/results/test_polymath_zh_high_evaluation.json +0 -30
- wisent/examples/scripts/results/test_polymath_zh_high_pairs.json +0 -8
- wisent/examples/scripts/results/test_polymath_zh_medium_evaluation.json +0 -30
- wisent/examples/scripts/results/test_polymath_zh_medium_pairs.json +0 -8
- wisent/examples/scripts/results/test_portuguese_bench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_portuguese_bench_pairs.json +0 -14
- wisent/examples/scripts/results/test_prompt_robustness_agieval_aqua_rat/test_prompt_robustness_agieval_aqua_rat_evaluation.json +0 -30
- wisent/examples/scripts/results/test_prompt_robustness_agieval_aqua_rat/test_prompt_robustness_agieval_aqua_rat_pairs.json +0 -8
- wisent/examples/scripts/results/test_prompt_robustness_agieval_aqua_rat_evaluation.json +0 -30
- wisent/examples/scripts/results/test_prompt_robustness_agieval_aqua_rat_pairs.json +0 -8
- wisent/examples/scripts/results/test_prost_evaluation.json +0 -30
- wisent/examples/scripts/results/test_prost_pairs.json +0 -8
- wisent/examples/scripts/results/test_ptb_evaluation.json +0 -30
- wisent/examples/scripts/results/test_ptb_pairs.json +0 -8
- wisent/examples/scripts/results/test_pubmedqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_pubmedqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_pythia_evaluation.json +0 -51
- wisent/examples/scripts/results/test_pythia_pairs.json +0 -14
- wisent/examples/scripts/results/test_qa4mre_evaluation.json +0 -30
- wisent/examples/scripts/results/test_qa4mre_pairs.json +0 -8
- wisent/examples/scripts/results/test_qasper_evaluation.json +0 -30
- wisent/examples/scripts/results/test_qasper_pairs.json +0 -8
- wisent/examples/scripts/results/test_race_evaluation.json +0 -30
- wisent/examples/scripts/results/test_race_pairs.json +0 -8
- wisent/examples/scripts/results/test_realtoxicityprompts_evaluation.json +0 -30
- wisent/examples/scripts/results/test_realtoxicityprompts_pairs.json +0 -8
- wisent/examples/scripts/results/test_recode_evaluation.json +0 -30
- wisent/examples/scripts/results/test_recode_pairs.json +0 -8
- wisent/examples/scripts/results/test_record_evaluation.json +0 -30
- wisent/examples/scripts/results/test_record_pairs.json +0 -8
- wisent/examples/scripts/results/test_ruler_evaluation.json +0 -51
- wisent/examples/scripts/results/test_ruler_pairs.json +0 -14
- wisent/examples/scripts/results/test_sciq_evaluation.json +0 -30
- wisent/examples/scripts/results/test_sciq_pairs.json +0 -8
- wisent/examples/scripts/results/test_score_evaluation.json +0 -51
- wisent/examples/scripts/results/test_score_pairs.json +0 -14
- wisent/examples/scripts/results/test_self_consistency_evaluation.json +0 -30
- wisent/examples/scripts/results/test_self_consistency_pairs.json +0 -8
- wisent/examples/scripts/results/test_siqa/test_siqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_siqa/test_siqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_siqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_siqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_spanish_bench_evaluation.json +0 -51
- wisent/examples/scripts/results/test_spanish_bench_pairs.json +0 -14
- wisent/examples/scripts/results/test_squad2_evaluation.json +0 -30
- wisent/examples/scripts/results/test_squad2_pairs.json +0 -8
- wisent/examples/scripts/results/test_squadv2_evaluation.json +0 -30
- wisent/examples/scripts/results/test_squadv2_pairs.json +0 -8
- wisent/examples/scripts/results/test_super-glue-lm-eval-v1-seq2seq_evaluation.json +0 -30
- wisent/examples/scripts/results/test_super-glue-lm-eval-v1-seq2seq_pairs.json +0 -8
- wisent/examples/scripts/results/test_super-glue-lm-eval-v1_evaluation.json +0 -51
- wisent/examples/scripts/results/test_super-glue-lm-eval-v1_pairs.json +0 -14
- wisent/examples/scripts/results/test_swag_evaluation.json +0 -30
- wisent/examples/scripts/results/test_swag_pairs.json +0 -8
- wisent/examples/scripts/results/test_tinyBenchmarks_evaluation.json +0 -51
- wisent/examples/scripts/results/test_tinyBenchmarks_pairs.json +0 -14
- wisent/examples/scripts/results/test_tmmluplus_evaluation.json +0 -51
- wisent/examples/scripts/results/test_tmmluplus_pairs.json +0 -14
- wisent/examples/scripts/results/test_translation_evaluation.json +0 -51
- wisent/examples/scripts/results/test_translation_pairs.json +0 -14
- wisent/examples/scripts/results/test_triviaqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_triviaqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_truthfulqa-multi_evaluation.json +0 -51
- wisent/examples/scripts/results/test_truthfulqa-multi_pairs.json +0 -14
- wisent/examples/scripts/results/test_truthfulqa_evaluation.json +0 -30
- wisent/examples/scripts/results/test_truthfulqa_mc1_evaluation.json +0 -30
- wisent/examples/scripts/results/test_truthfulqa_mc1_pairs.json +0 -8
- wisent/examples/scripts/results/test_truthfulqa_mc2_evaluation.json +0 -30
- wisent/examples/scripts/results/test_truthfulqa_mc2_pairs.json +0 -8
- wisent/examples/scripts/results/test_truthfulqa_pairs.json +0 -8
- wisent/examples/scripts/results/test_turkishmmlu_evaluation.json +0 -51
- wisent/examples/scripts/results/test_turkishmmlu_pairs.json +0 -14
- wisent/examples/scripts/results/test_unfair_tos_evaluation.json +0 -30
- wisent/examples/scripts/results/test_unfair_tos_pairs.json +0 -8
- wisent/examples/scripts/results/test_unscramble_evaluation.json +0 -51
- wisent/examples/scripts/results/test_unscramble_pairs.json +0 -14
- wisent/examples/scripts/results/test_webqs_evaluation.json +0 -30
- wisent/examples/scripts/results/test_webqs_pairs.json +0 -8
- wisent/examples/scripts/results/test_wikitext103_evaluation.json +0 -30
- wisent/examples/scripts/results/test_wikitext103_pairs.json +0 -8
- wisent/examples/scripts/results/test_wikitext_evaluation.json +0 -30
- wisent/examples/scripts/results/test_wikitext_pairs.json +0 -8
- wisent/examples/scripts/results/test_winogender_evaluation.json +0 -51
- wisent/examples/scripts/results/test_winogender_pairs.json +0 -14
- wisent/examples/scripts/results/test_winogrande_evaluation.json +0 -30
- wisent/examples/scripts/results/test_winogrande_pairs.json +0 -8
- wisent/examples/scripts/results/test_wmdp_evaluation.json +0 -30
- wisent/examples/scripts/results/test_wmdp_pairs.json +0 -8
- wisent/examples/scripts/results/test_wmt-ro-en-t5-prompt_evaluation.json +0 -30
- wisent/examples/scripts/results/test_wmt-ro-en-t5-prompt_pairs.json +0 -8
- wisent/examples/scripts/results/test_wmt14_en_fr_evaluation.json +0 -30
- wisent/examples/scripts/results/test_wmt14_en_fr_pairs.json +0 -8
- wisent/examples/scripts/results/test_wmt16_en_de_evaluation.json +0 -30
- wisent/examples/scripts/results/test_wmt16_en_de_pairs.json +0 -8
- wisent/examples/scripts/results/test_wmt16_ro_en_evaluation.json +0 -30
- wisent/examples/scripts/results/test_wmt16_ro_en_pairs.json +0 -8
- wisent/examples/scripts/results/test_wsc273_evaluation.json +0 -30
- wisent/examples/scripts/results/test_wsc273_pairs.json +0 -8
- wisent/examples/scripts/results/test_xcopa_evaluation.json +0 -51
- wisent/examples/scripts/results/test_xcopa_pairs.json +0 -14
- wisent/examples/scripts/results/test_xnli_eu_evaluation.json +0 -30
- wisent/examples/scripts/results/test_xnli_eu_pairs.json +0 -8
- wisent/examples/scripts/results/test_xnli_evaluation.json +0 -51
- wisent/examples/scripts/results/test_xnli_pairs.json +0 -14
- wisent/examples/scripts/results/test_xquad_evaluation.json +0 -51
- wisent/examples/scripts/results/test_xquad_pairs.json +0 -14
- wisent/examples/scripts/results/test_xstorycloze_evaluation.json +0 -51
- wisent/examples/scripts/results/test_xstorycloze_pairs.json +0 -14
- wisent/examples/scripts/results/test_xsum_evaluation.json +0 -30
- wisent/examples/scripts/results/test_xsum_pairs.json +0 -8
- wisent/examples/scripts/results/test_xwinograd_evaluation.json +0 -51
- wisent/examples/scripts/results/test_xwinograd_pairs.json +0 -14
- wisent/examples/scripts/results/test_yahoo_answers_topics_evaluation.json +0 -30
- wisent/examples/scripts/results/test_yahoo_answers_topics_pairs.json +0 -8
- {wisent-0.7.379.dist-info → wisent-0.7.901.dist-info}/WHEEL +0 -0
- {wisent-0.7.379.dist-info → wisent-0.7.901.dist-info}/entry_points.txt +0 -0
- {wisent-0.7.379.dist-info → wisent-0.7.901.dist-info}/licenses/LICENSE +0 -0
- {wisent-0.7.379.dist-info → wisent-0.7.901.dist-info}/top_level.txt +0 -0
|
@@ -1,945 +0,0 @@
|
|
|
1
|
-
{
|
|
2
|
-
"model": "mock",
|
|
3
|
-
"total": 235,
|
|
4
|
-
"passed": 40,
|
|
5
|
-
"failed": 195,
|
|
6
|
-
"timeout": 0,
|
|
7
|
-
"benchmarks": {
|
|
8
|
-
"math500": {
|
|
9
|
-
"status": "passed",
|
|
10
|
-
"success": true
|
|
11
|
-
},
|
|
12
|
-
"aime2024": {
|
|
13
|
-
"status": "passed",
|
|
14
|
-
"success": true
|
|
15
|
-
},
|
|
16
|
-
"aime2025": {
|
|
17
|
-
"status": "passed",
|
|
18
|
-
"success": true
|
|
19
|
-
},
|
|
20
|
-
"hmmt": {
|
|
21
|
-
"status": "passed",
|
|
22
|
-
"success": true
|
|
23
|
-
},
|
|
24
|
-
"hmmt_feb_2025": {
|
|
25
|
-
"status": "passed",
|
|
26
|
-
"success": true
|
|
27
|
-
},
|
|
28
|
-
"polymath_en_medium": {
|
|
29
|
-
"status": "passed",
|
|
30
|
-
"success": true
|
|
31
|
-
},
|
|
32
|
-
"polymath_zh_medium": {
|
|
33
|
-
"status": "passed",
|
|
34
|
-
"success": true
|
|
35
|
-
},
|
|
36
|
-
"polymath_en_high": {
|
|
37
|
-
"status": "passed",
|
|
38
|
-
"success": true
|
|
39
|
-
},
|
|
40
|
-
"polymath_zh_high": {
|
|
41
|
-
"status": "passed",
|
|
42
|
-
"success": true
|
|
43
|
-
},
|
|
44
|
-
"livemathbench_cnmo_en": {
|
|
45
|
-
"status": "passed",
|
|
46
|
-
"success": true
|
|
47
|
-
},
|
|
48
|
-
"livemathbench_cnmo_zh": {
|
|
49
|
-
"status": "failed",
|
|
50
|
-
"success": false
|
|
51
|
-
},
|
|
52
|
-
"instruct_humaneval": {
|
|
53
|
-
"status": "failed",
|
|
54
|
-
"success": false
|
|
55
|
-
},
|
|
56
|
-
"recode": {
|
|
57
|
-
"status": "failed",
|
|
58
|
-
"success": false
|
|
59
|
-
},
|
|
60
|
-
"bbh": {
|
|
61
|
-
"status": "passed",
|
|
62
|
-
"success": true
|
|
63
|
-
},
|
|
64
|
-
"siqa": {
|
|
65
|
-
"status": "failed",
|
|
66
|
-
"success": false
|
|
67
|
-
},
|
|
68
|
-
"AraDICE": {
|
|
69
|
-
"status": "failed",
|
|
70
|
-
"success": false
|
|
71
|
-
},
|
|
72
|
-
"ArabCulture": {
|
|
73
|
-
"status": "failed",
|
|
74
|
-
"success": false
|
|
75
|
-
},
|
|
76
|
-
"darija_bench": {
|
|
77
|
-
"status": "failed",
|
|
78
|
-
"success": false
|
|
79
|
-
},
|
|
80
|
-
"ceval": {
|
|
81
|
-
"status": "failed",
|
|
82
|
-
"success": false
|
|
83
|
-
},
|
|
84
|
-
"turkishmmlu": {
|
|
85
|
-
"status": "failed",
|
|
86
|
-
"success": false
|
|
87
|
-
},
|
|
88
|
-
"bangla_mmlu": {
|
|
89
|
-
"status": "failed",
|
|
90
|
-
"success": false
|
|
91
|
-
},
|
|
92
|
-
"japanese_leaderboard": {
|
|
93
|
-
"status": "failed",
|
|
94
|
-
"success": false
|
|
95
|
-
},
|
|
96
|
-
"kormedmcqa": {
|
|
97
|
-
"status": "failed",
|
|
98
|
-
"success": false
|
|
99
|
-
},
|
|
100
|
-
"basqueglue": {
|
|
101
|
-
"status": "failed",
|
|
102
|
-
"success": false
|
|
103
|
-
},
|
|
104
|
-
"eus_exams": {
|
|
105
|
-
"status": "failed",
|
|
106
|
-
"success": false
|
|
107
|
-
},
|
|
108
|
-
"catalan_bench": {
|
|
109
|
-
"status": "failed",
|
|
110
|
-
"success": false
|
|
111
|
-
},
|
|
112
|
-
"french_bench": {
|
|
113
|
-
"status": "failed",
|
|
114
|
-
"success": false
|
|
115
|
-
},
|
|
116
|
-
"icelandic_winogrande": {
|
|
117
|
-
"status": "failed",
|
|
118
|
-
"success": false
|
|
119
|
-
},
|
|
120
|
-
"global_mmlu": {
|
|
121
|
-
"status": "failed",
|
|
122
|
-
"success": false
|
|
123
|
-
},
|
|
124
|
-
"global_piqa": {
|
|
125
|
-
"status": "failed",
|
|
126
|
-
"success": false
|
|
127
|
-
},
|
|
128
|
-
"belebele": {
|
|
129
|
-
"status": "failed",
|
|
130
|
-
"success": false
|
|
131
|
-
},
|
|
132
|
-
"mlqa": {
|
|
133
|
-
"status": "failed",
|
|
134
|
-
"success": false
|
|
135
|
-
},
|
|
136
|
-
"xquad": {
|
|
137
|
-
"status": "failed",
|
|
138
|
-
"success": false
|
|
139
|
-
},
|
|
140
|
-
"xcopa": {
|
|
141
|
-
"status": "failed",
|
|
142
|
-
"success": false
|
|
143
|
-
},
|
|
144
|
-
"okapi/arc_multilingual": {
|
|
145
|
-
"status": "failed",
|
|
146
|
-
"success": false
|
|
147
|
-
},
|
|
148
|
-
"okapi/hellaswag_multilingual": {
|
|
149
|
-
"status": "failed",
|
|
150
|
-
"success": false
|
|
151
|
-
},
|
|
152
|
-
"okapi/mmlu_multilingual": {
|
|
153
|
-
"status": "failed",
|
|
154
|
-
"success": false
|
|
155
|
-
},
|
|
156
|
-
"okapi/truthfulqa_multilingual": {
|
|
157
|
-
"status": "failed",
|
|
158
|
-
"success": false
|
|
159
|
-
},
|
|
160
|
-
"toxigen": {
|
|
161
|
-
"status": "failed",
|
|
162
|
-
"success": false
|
|
163
|
-
},
|
|
164
|
-
"moral_stories": {
|
|
165
|
-
"status": "failed",
|
|
166
|
-
"success": false
|
|
167
|
-
},
|
|
168
|
-
"realtoxicityprompts": {
|
|
169
|
-
"status": "failed",
|
|
170
|
-
"success": false
|
|
171
|
-
},
|
|
172
|
-
"discrim_eval": {
|
|
173
|
-
"status": "failed",
|
|
174
|
-
"success": false
|
|
175
|
-
},
|
|
176
|
-
"esbbq": {
|
|
177
|
-
"status": "failed",
|
|
178
|
-
"success": false
|
|
179
|
-
},
|
|
180
|
-
"cabbq": {
|
|
181
|
-
"status": "failed",
|
|
182
|
-
"success": false
|
|
183
|
-
},
|
|
184
|
-
"simple_cooccurrence_bias": {
|
|
185
|
-
"status": "failed",
|
|
186
|
-
"success": false
|
|
187
|
-
},
|
|
188
|
-
"winogender": {
|
|
189
|
-
"status": "failed",
|
|
190
|
-
"success": false
|
|
191
|
-
},
|
|
192
|
-
"medmcqa": {
|
|
193
|
-
"status": "failed",
|
|
194
|
-
"success": false
|
|
195
|
-
},
|
|
196
|
-
"med_concepts_qa": {
|
|
197
|
-
"status": "failed",
|
|
198
|
-
"success": false
|
|
199
|
-
},
|
|
200
|
-
"meddialog": {
|
|
201
|
-
"status": "failed",
|
|
202
|
-
"success": false
|
|
203
|
-
},
|
|
204
|
-
"mediqa_qa2019": {
|
|
205
|
-
"status": "failed",
|
|
206
|
-
"success": false
|
|
207
|
-
},
|
|
208
|
-
"medtext": {
|
|
209
|
-
"status": "failed",
|
|
210
|
-
"success": false
|
|
211
|
-
},
|
|
212
|
-
"meqsum": {
|
|
213
|
-
"status": "failed",
|
|
214
|
-
"success": false
|
|
215
|
-
},
|
|
216
|
-
"mimic_repsum": {
|
|
217
|
-
"status": "failed",
|
|
218
|
-
"success": false
|
|
219
|
-
},
|
|
220
|
-
"minerva_math": {
|
|
221
|
-
"status": "failed",
|
|
222
|
-
"success": false
|
|
223
|
-
},
|
|
224
|
-
"mgsm": {
|
|
225
|
-
"status": "failed",
|
|
226
|
-
"success": false
|
|
227
|
-
},
|
|
228
|
-
"hrm8k": {
|
|
229
|
-
"status": "failed",
|
|
230
|
-
"success": false
|
|
231
|
-
},
|
|
232
|
-
"babi": {
|
|
233
|
-
"status": "failed",
|
|
234
|
-
"success": false
|
|
235
|
-
},
|
|
236
|
-
"babilong": {
|
|
237
|
-
"status": "failed",
|
|
238
|
-
"success": false
|
|
239
|
-
},
|
|
240
|
-
"longbench": {
|
|
241
|
-
"status": "failed",
|
|
242
|
-
"success": false
|
|
243
|
-
},
|
|
244
|
-
"longbenchv2": {
|
|
245
|
-
"status": "failed",
|
|
246
|
-
"success": false
|
|
247
|
-
},
|
|
248
|
-
"ruler": {
|
|
249
|
-
"status": "failed",
|
|
250
|
-
"success": false
|
|
251
|
-
},
|
|
252
|
-
"scrolls": {
|
|
253
|
-
"status": "failed",
|
|
254
|
-
"success": false
|
|
255
|
-
},
|
|
256
|
-
"inverse_scaling": {
|
|
257
|
-
"status": "failed",
|
|
258
|
-
"success": false
|
|
259
|
-
},
|
|
260
|
-
"storycloze": {
|
|
261
|
-
"status": "failed",
|
|
262
|
-
"success": false
|
|
263
|
-
},
|
|
264
|
-
"histoires_morales": {
|
|
265
|
-
"status": "failed",
|
|
266
|
-
"success": false
|
|
267
|
-
},
|
|
268
|
-
"groundcocoa": {
|
|
269
|
-
"status": "failed",
|
|
270
|
-
"success": false
|
|
271
|
-
},
|
|
272
|
-
"blimp": {
|
|
273
|
-
"status": "passed",
|
|
274
|
-
"success": true
|
|
275
|
-
},
|
|
276
|
-
"blimp_nl": {
|
|
277
|
-
"status": "failed",
|
|
278
|
-
"success": false
|
|
279
|
-
},
|
|
280
|
-
"multiblimp": {
|
|
281
|
-
"status": "failed",
|
|
282
|
-
"success": false
|
|
283
|
-
},
|
|
284
|
-
"turblimp_core": {
|
|
285
|
-
"status": "failed",
|
|
286
|
-
"success": false
|
|
287
|
-
},
|
|
288
|
-
"zhoblimp": {
|
|
289
|
-
"status": "failed",
|
|
290
|
-
"success": false
|
|
291
|
-
},
|
|
292
|
-
"lambada_multilingual_stablelm": {
|
|
293
|
-
"status": "failed",
|
|
294
|
-
"success": false
|
|
295
|
-
},
|
|
296
|
-
"paws-x": {
|
|
297
|
-
"status": "failed",
|
|
298
|
-
"success": false
|
|
299
|
-
},
|
|
300
|
-
"translation": {
|
|
301
|
-
"status": "failed",
|
|
302
|
-
"success": false
|
|
303
|
-
},
|
|
304
|
-
"wmt2016": {
|
|
305
|
-
"status": "failed",
|
|
306
|
-
"success": false
|
|
307
|
-
},
|
|
308
|
-
"code_x_glue": {
|
|
309
|
-
"status": "failed",
|
|
310
|
-
"success": false
|
|
311
|
-
},
|
|
312
|
-
"humaneval_infilling": {
|
|
313
|
-
"status": "failed",
|
|
314
|
-
"success": false
|
|
315
|
-
},
|
|
316
|
-
"bertaqa": {
|
|
317
|
-
"status": "failed",
|
|
318
|
-
"success": false
|
|
319
|
-
},
|
|
320
|
-
"careqa": {
|
|
321
|
-
"status": "failed",
|
|
322
|
-
"success": false
|
|
323
|
-
},
|
|
324
|
-
"acp_bench": {
|
|
325
|
-
"status": "failed",
|
|
326
|
-
"success": false
|
|
327
|
-
},
|
|
328
|
-
"acp_bench_hard": {
|
|
329
|
-
"status": "failed",
|
|
330
|
-
"success": false
|
|
331
|
-
},
|
|
332
|
-
"aexams": {
|
|
333
|
-
"status": "failed",
|
|
334
|
-
"success": false
|
|
335
|
-
},
|
|
336
|
-
"benchmarks": {
|
|
337
|
-
"status": "failed",
|
|
338
|
-
"success": false
|
|
339
|
-
},
|
|
340
|
-
"bhs": {
|
|
341
|
-
"status": "failed",
|
|
342
|
-
"success": false
|
|
343
|
-
},
|
|
344
|
-
"c4": {
|
|
345
|
-
"status": "failed",
|
|
346
|
-
"success": false
|
|
347
|
-
},
|
|
348
|
-
"chartqa": {
|
|
349
|
-
"status": "failed",
|
|
350
|
-
"success": false
|
|
351
|
-
},
|
|
352
|
-
"click": {
|
|
353
|
-
"status": "failed",
|
|
354
|
-
"success": false
|
|
355
|
-
},
|
|
356
|
-
"eq-bench_ca": {
|
|
357
|
-
"status": "failed",
|
|
358
|
-
"success": false
|
|
359
|
-
},
|
|
360
|
-
"eq-bench_es": {
|
|
361
|
-
"status": "failed",
|
|
362
|
-
"success": false
|
|
363
|
-
},
|
|
364
|
-
"evalita_LLM": {
|
|
365
|
-
"status": "failed",
|
|
366
|
-
"success": false
|
|
367
|
-
},
|
|
368
|
-
"fda": {
|
|
369
|
-
"status": "failed",
|
|
370
|
-
"success": false
|
|
371
|
-
},
|
|
372
|
-
"fld": {
|
|
373
|
-
"status": "failed",
|
|
374
|
-
"success": false
|
|
375
|
-
},
|
|
376
|
-
"jsonschema_bench": {
|
|
377
|
-
"status": "failed",
|
|
378
|
-
"success": false
|
|
379
|
-
},
|
|
380
|
-
"kbl": {
|
|
381
|
-
"status": "failed",
|
|
382
|
-
"success": false
|
|
383
|
-
},
|
|
384
|
-
"leaderboard": {
|
|
385
|
-
"status": "failed",
|
|
386
|
-
"success": false
|
|
387
|
-
},
|
|
388
|
-
"libra": {
|
|
389
|
-
"status": "failed",
|
|
390
|
-
"success": false
|
|
391
|
-
},
|
|
392
|
-
"lingoly": {
|
|
393
|
-
"status": "failed",
|
|
394
|
-
"success": false
|
|
395
|
-
},
|
|
396
|
-
"llama3": {
|
|
397
|
-
"status": "failed",
|
|
398
|
-
"success": false
|
|
399
|
-
},
|
|
400
|
-
"lm_syneval": {
|
|
401
|
-
"status": "failed",
|
|
402
|
-
"success": false
|
|
403
|
-
},
|
|
404
|
-
"mastermind": {
|
|
405
|
-
"status": "failed",
|
|
406
|
-
"success": false
|
|
407
|
-
},
|
|
408
|
-
"mmlusr": {
|
|
409
|
-
"status": "failed",
|
|
410
|
-
"success": false
|
|
411
|
-
},
|
|
412
|
-
"mmmu": {
|
|
413
|
-
"status": "failed",
|
|
414
|
-
"success": false
|
|
415
|
-
},
|
|
416
|
-
"model_written_evals": {
|
|
417
|
-
"status": "failed",
|
|
418
|
-
"success": false
|
|
419
|
-
},
|
|
420
|
-
"mts_dialog": {
|
|
421
|
-
"status": "failed",
|
|
422
|
-
"success": false
|
|
423
|
-
},
|
|
424
|
-
"noreval": {
|
|
425
|
-
"status": "failed",
|
|
426
|
-
"success": false
|
|
427
|
-
},
|
|
428
|
-
"olaph": {
|
|
429
|
-
"status": "failed",
|
|
430
|
-
"success": false
|
|
431
|
-
},
|
|
432
|
-
"paloma": {
|
|
433
|
-
"status": "failed",
|
|
434
|
-
"success": false
|
|
435
|
-
},
|
|
436
|
-
"pile": {
|
|
437
|
-
"status": "failed",
|
|
438
|
-
"success": false
|
|
439
|
-
},
|
|
440
|
-
"pile_10k": {
|
|
441
|
-
"status": "failed",
|
|
442
|
-
"success": false
|
|
443
|
-
},
|
|
444
|
-
"polemo2": {
|
|
445
|
-
"status": "failed",
|
|
446
|
-
"success": false
|
|
447
|
-
},
|
|
448
|
-
"score": {
|
|
449
|
-
"status": "failed",
|
|
450
|
-
"success": false
|
|
451
|
-
},
|
|
452
|
-
"squad_completion": {
|
|
453
|
-
"status": "failed",
|
|
454
|
-
"success": false
|
|
455
|
-
},
|
|
456
|
-
"super_glue": {
|
|
457
|
-
"status": "failed",
|
|
458
|
-
"success": false
|
|
459
|
-
},
|
|
460
|
-
"swde": {
|
|
461
|
-
"status": "failed",
|
|
462
|
-
"success": false
|
|
463
|
-
},
|
|
464
|
-
"tinyBenchmarks": {
|
|
465
|
-
"status": "failed",
|
|
466
|
-
"success": false
|
|
467
|
-
},
|
|
468
|
-
"truthfulqa-multi": {
|
|
469
|
-
"status": "failed",
|
|
470
|
-
"success": false
|
|
471
|
-
},
|
|
472
|
-
"unitxt": {
|
|
473
|
-
"status": "failed",
|
|
474
|
-
"success": false
|
|
475
|
-
},
|
|
476
|
-
"unscramble": {
|
|
477
|
-
"status": "passed",
|
|
478
|
-
"success": true
|
|
479
|
-
},
|
|
480
|
-
"wmdp": {
|
|
481
|
-
"status": "passed",
|
|
482
|
-
"success": true
|
|
483
|
-
},
|
|
484
|
-
"wsc273": {
|
|
485
|
-
"status": "failed",
|
|
486
|
-
"success": false
|
|
487
|
-
},
|
|
488
|
-
"global_mmlu_ar": {
|
|
489
|
-
"status": "failed",
|
|
490
|
-
"success": false
|
|
491
|
-
},
|
|
492
|
-
"arabic_exams": {
|
|
493
|
-
"status": "passed",
|
|
494
|
-
"success": true
|
|
495
|
-
},
|
|
496
|
-
"persona": {
|
|
497
|
-
"status": "failed",
|
|
498
|
-
"success": false
|
|
499
|
-
},
|
|
500
|
-
"afrixnli_en_direct_amh": {
|
|
501
|
-
"status": "failed",
|
|
502
|
-
"success": false
|
|
503
|
-
},
|
|
504
|
-
"evalita_mp": {
|
|
505
|
-
"status": "failed",
|
|
506
|
-
"success": false
|
|
507
|
-
},
|
|
508
|
-
"truthfulqa": {
|
|
509
|
-
"status": "passed",
|
|
510
|
-
"success": true
|
|
511
|
-
},
|
|
512
|
-
"eus_exams_es": {
|
|
513
|
-
"status": "passed",
|
|
514
|
-
"success": true
|
|
515
|
-
},
|
|
516
|
-
"flores": {
|
|
517
|
-
"status": "failed",
|
|
518
|
-
"success": false
|
|
519
|
-
},
|
|
520
|
-
"afrimgsm_direct_amh": {
|
|
521
|
-
"status": "failed",
|
|
522
|
-
"success": false
|
|
523
|
-
},
|
|
524
|
-
"ceval_valid": {
|
|
525
|
-
"status": "failed",
|
|
526
|
-
"success": false
|
|
527
|
-
},
|
|
528
|
-
"advanced_ai_risk": {
|
|
529
|
-
"status": "failed",
|
|
530
|
-
"success": false
|
|
531
|
-
},
|
|
532
|
-
"tmlu": {
|
|
533
|
-
"status": "failed",
|
|
534
|
-
"success": false
|
|
535
|
-
},
|
|
536
|
-
"arc_ar": {
|
|
537
|
-
"status": "failed",
|
|
538
|
-
"success": false
|
|
539
|
-
},
|
|
540
|
-
"afrimmlu_direct_amh": {
|
|
541
|
-
"status": "failed",
|
|
542
|
-
"success": false
|
|
543
|
-
},
|
|
544
|
-
"m_mmlu": {
|
|
545
|
-
"status": "passed",
|
|
546
|
-
"success": true
|
|
547
|
-
},
|
|
548
|
-
"non_greedy_robustness_agieval_aqua_rat": {
|
|
549
|
-
"status": "passed",
|
|
550
|
-
"success": true
|
|
551
|
-
},
|
|
552
|
-
"prompt_robustness_agieval_aqua_rat": {
|
|
553
|
-
"status": "passed",
|
|
554
|
-
"success": true
|
|
555
|
-
},
|
|
556
|
-
"inverse_scaling_hindsight_neglect_10shot": {
|
|
557
|
-
"status": "failed",
|
|
558
|
-
"success": false
|
|
559
|
-
},
|
|
560
|
-
"mela": {
|
|
561
|
-
"status": "failed",
|
|
562
|
-
"success": false
|
|
563
|
-
},
|
|
564
|
-
"paws_ca": {
|
|
565
|
-
"status": "failed",
|
|
566
|
-
"success": false
|
|
567
|
-
},
|
|
568
|
-
"ja_leaderboard_jaqket_v2": {
|
|
569
|
-
"status": "failed",
|
|
570
|
-
"success": false
|
|
571
|
-
},
|
|
572
|
-
"super_glue-boolq-t5-prompt": {
|
|
573
|
-
"status": "failed",
|
|
574
|
-
"success": false
|
|
575
|
-
},
|
|
576
|
-
"multiple_choice": {
|
|
577
|
-
"status": "failed",
|
|
578
|
-
"success": false
|
|
579
|
-
},
|
|
580
|
-
"option_order_robustness_agieval_aqua_rat": {
|
|
581
|
-
"status": "passed",
|
|
582
|
-
"success": true
|
|
583
|
-
},
|
|
584
|
-
"phrases_ca-va": {
|
|
585
|
-
"status": "failed",
|
|
586
|
-
"success": false
|
|
587
|
-
},
|
|
588
|
-
"code2text_go": {
|
|
589
|
-
"status": "failed",
|
|
590
|
-
"success": false
|
|
591
|
-
},
|
|
592
|
-
"ethics_cm": {
|
|
593
|
-
"status": "passed",
|
|
594
|
-
"success": true
|
|
595
|
-
},
|
|
596
|
-
"cabreu": {
|
|
597
|
-
"status": "failed",
|
|
598
|
-
"success": false
|
|
599
|
-
},
|
|
600
|
-
"sycophancy": {
|
|
601
|
-
"status": "failed",
|
|
602
|
-
"success": false
|
|
603
|
-
},
|
|
604
|
-
"evalita_sp_sum_task_fp-small_p1": {
|
|
605
|
-
"status": "failed",
|
|
606
|
-
"success": false
|
|
607
|
-
},
|
|
608
|
-
"glianorex": {
|
|
609
|
-
"status": "passed",
|
|
610
|
-
"success": true
|
|
611
|
-
},
|
|
612
|
-
"flan_held_in": {
|
|
613
|
-
"status": "failed",
|
|
614
|
-
"success": false
|
|
615
|
-
},
|
|
616
|
-
"assin_entailment": {
|
|
617
|
-
"status": "passed",
|
|
618
|
-
"success": true
|
|
619
|
-
},
|
|
620
|
-
"gsm_plus": {
|
|
621
|
-
"status": "failed",
|
|
622
|
-
"success": false
|
|
623
|
-
},
|
|
624
|
-
"mnli": {
|
|
625
|
-
"status": "failed",
|
|
626
|
-
"success": false
|
|
627
|
-
},
|
|
628
|
-
"tinyTruthfulQA": {
|
|
629
|
-
"status": "failed",
|
|
630
|
-
"success": false
|
|
631
|
-
},
|
|
632
|
-
"multimedqa": {
|
|
633
|
-
"status": "passed",
|
|
634
|
-
"success": true
|
|
635
|
-
},
|
|
636
|
-
"openllm": {
|
|
637
|
-
"status": "passed",
|
|
638
|
-
"success": true
|
|
639
|
-
},
|
|
640
|
-
"pythia": {
|
|
641
|
-
"status": "passed",
|
|
642
|
-
"success": true
|
|
643
|
-
},
|
|
644
|
-
"t0_eval": {
|
|
645
|
-
"status": "failed",
|
|
646
|
-
"success": false
|
|
647
|
-
},
|
|
648
|
-
"Tag": {
|
|
649
|
-
"status": "failed",
|
|
650
|
-
"success": false
|
|
651
|
-
},
|
|
652
|
-
"basque-glue": {
|
|
653
|
-
"status": "failed",
|
|
654
|
-
"success": false
|
|
655
|
-
},
|
|
656
|
-
"chain_of_thought": {
|
|
657
|
-
"status": "passed",
|
|
658
|
-
"success": true
|
|
659
|
-
},
|
|
660
|
-
"freebase": {
|
|
661
|
-
"status": "passed",
|
|
662
|
-
"success": true
|
|
663
|
-
},
|
|
664
|
-
"gpt3_translation_benchmarks": {
|
|
665
|
-
"status": "failed",
|
|
666
|
-
"success": false
|
|
667
|
-
},
|
|
668
|
-
"iwslt2017": {
|
|
669
|
-
"status": "failed",
|
|
670
|
-
"success": false
|
|
671
|
-
},
|
|
672
|
-
"llama": {
|
|
673
|
-
"status": "passed",
|
|
674
|
-
"success": true
|
|
675
|
-
},
|
|
676
|
-
"self_consistency": {
|
|
677
|
-
"status": "passed",
|
|
678
|
-
"success": true
|
|
679
|
-
},
|
|
680
|
-
"super-glue-lm-eval-v1": {
|
|
681
|
-
"status": "failed",
|
|
682
|
-
"success": false
|
|
683
|
-
},
|
|
684
|
-
"super-glue-lm-eval-v1-seq2seq": {
|
|
685
|
-
"status": "failed",
|
|
686
|
-
"success": false
|
|
687
|
-
},
|
|
688
|
-
"super-glue-t5-prompt": {
|
|
689
|
-
"status": "failed",
|
|
690
|
-
"success": false
|
|
691
|
-
},
|
|
692
|
-
"wmt14": {
|
|
693
|
-
"status": "failed",
|
|
694
|
-
"success": false
|
|
695
|
-
},
|
|
696
|
-
"wmt14_en_fr": {
|
|
697
|
-
"status": "failed",
|
|
698
|
-
"success": false
|
|
699
|
-
},
|
|
700
|
-
"wmt14_fr_en": {
|
|
701
|
-
"status": "failed",
|
|
702
|
-
"success": false
|
|
703
|
-
},
|
|
704
|
-
"wmt16_de_en": {
|
|
705
|
-
"status": "failed",
|
|
706
|
-
"success": false
|
|
707
|
-
},
|
|
708
|
-
"wmt16_en_de": {
|
|
709
|
-
"status": "failed",
|
|
710
|
-
"success": false
|
|
711
|
-
},
|
|
712
|
-
"wmt16_en_ro": {
|
|
713
|
-
"status": "failed",
|
|
714
|
-
"success": false
|
|
715
|
-
},
|
|
716
|
-
"wmt16_ro_en": {
|
|
717
|
-
"status": "failed",
|
|
718
|
-
"success": false
|
|
719
|
-
},
|
|
720
|
-
"20_newsgroups": {
|
|
721
|
-
"status": "passed",
|
|
722
|
-
"success": true
|
|
723
|
-
},
|
|
724
|
-
"ag_news": {
|
|
725
|
-
"status": "passed",
|
|
726
|
-
"success": true
|
|
727
|
-
},
|
|
728
|
-
"anagrams1": {
|
|
729
|
-
"status": "passed",
|
|
730
|
-
"success": true
|
|
731
|
-
},
|
|
732
|
-
"anagrams2": {
|
|
733
|
-
"status": "passed",
|
|
734
|
-
"success": true
|
|
735
|
-
},
|
|
736
|
-
"argument_topic": {
|
|
737
|
-
"status": "passed",
|
|
738
|
-
"success": true
|
|
739
|
-
},
|
|
740
|
-
"atis": {
|
|
741
|
-
"status": "failed",
|
|
742
|
-
"success": false
|
|
743
|
-
},
|
|
744
|
-
"banking77": {
|
|
745
|
-
"status": "passed",
|
|
746
|
-
"success": true
|
|
747
|
-
},
|
|
748
|
-
"bec2016eu": {
|
|
749
|
-
"status": "failed",
|
|
750
|
-
"success": false
|
|
751
|
-
},
|
|
752
|
-
"bhtc_v2": {
|
|
753
|
-
"status": "failed",
|
|
754
|
-
"success": false
|
|
755
|
-
},
|
|
756
|
-
"boolq-seq2seq": {
|
|
757
|
-
"status": "failed",
|
|
758
|
-
"success": false
|
|
759
|
-
},
|
|
760
|
-
"catalanqa": {
|
|
761
|
-
"status": "failed",
|
|
762
|
-
"success": false
|
|
763
|
-
},
|
|
764
|
-
"catcola": {
|
|
765
|
-
"status": "failed",
|
|
766
|
-
"success": false
|
|
767
|
-
},
|
|
768
|
-
"claim_stance_topic": {
|
|
769
|
-
"status": "failed",
|
|
770
|
-
"success": false
|
|
771
|
-
},
|
|
772
|
-
"cnn_dailymail": {
|
|
773
|
-
"status": "failed",
|
|
774
|
-
"success": false
|
|
775
|
-
},
|
|
776
|
-
"cocoteros_es": {
|
|
777
|
-
"status": "failed",
|
|
778
|
-
"success": false
|
|
779
|
-
},
|
|
780
|
-
"coedit_gec": {
|
|
781
|
-
"status": "failed",
|
|
782
|
-
"success": false
|
|
783
|
-
},
|
|
784
|
-
"cola": {
|
|
785
|
-
"status": "failed",
|
|
786
|
-
"success": false
|
|
787
|
-
},
|
|
788
|
-
"coqcat": {
|
|
789
|
-
"status": "failed",
|
|
790
|
-
"success": false
|
|
791
|
-
},
|
|
792
|
-
"cycle_letters": {
|
|
793
|
-
"status": "passed",
|
|
794
|
-
"success": true
|
|
795
|
-
},
|
|
796
|
-
"dbpedia_14": {
|
|
797
|
-
"status": "failed",
|
|
798
|
-
"success": false
|
|
799
|
-
},
|
|
800
|
-
"doc_vqa": {
|
|
801
|
-
"status": "failed",
|
|
802
|
-
"success": false
|
|
803
|
-
},
|
|
804
|
-
"epec_koref_bin": {
|
|
805
|
-
"status": "failed",
|
|
806
|
-
"success": false
|
|
807
|
-
},
|
|
808
|
-
"escola": {
|
|
809
|
-
"status": "passed",
|
|
810
|
-
"success": true
|
|
811
|
-
},
|
|
812
|
-
"ethos_binary": {
|
|
813
|
-
"status": "failed",
|
|
814
|
-
"success": false
|
|
815
|
-
},
|
|
816
|
-
"financial_tweets": {
|
|
817
|
-
"status": "failed",
|
|
818
|
-
"success": false
|
|
819
|
-
},
|
|
820
|
-
"galcola": {
|
|
821
|
-
"status": "passed",
|
|
822
|
-
"success": true
|
|
823
|
-
},
|
|
824
|
-
"iwslt2017-ar-en": {
|
|
825
|
-
"status": "failed",
|
|
826
|
-
"success": false
|
|
827
|
-
},
|
|
828
|
-
"iwslt2017-en-ar": {
|
|
829
|
-
"status": "failed",
|
|
830
|
-
"success": false
|
|
831
|
-
},
|
|
832
|
-
"law_stack_exchange": {
|
|
833
|
-
"status": "failed",
|
|
834
|
-
"success": false
|
|
835
|
-
},
|
|
836
|
-
"ledgar": {
|
|
837
|
-
"status": "failed",
|
|
838
|
-
"success": false
|
|
839
|
-
},
|
|
840
|
-
"logieval": {
|
|
841
|
-
"status": "failed",
|
|
842
|
-
"success": false
|
|
843
|
-
},
|
|
844
|
-
"medical_abstracts": {
|
|
845
|
-
"status": "failed",
|
|
846
|
-
"success": false
|
|
847
|
-
},
|
|
848
|
-
"noticia": {
|
|
849
|
-
"status": "failed",
|
|
850
|
-
"success": false
|
|
851
|
-
},
|
|
852
|
-
"parafraseja": {
|
|
853
|
-
"status": "failed",
|
|
854
|
-
"success": false
|
|
855
|
-
},
|
|
856
|
-
"parafrases_gl": {
|
|
857
|
-
"status": "failed",
|
|
858
|
-
"success": false
|
|
859
|
-
},
|
|
860
|
-
"qnlieu": {
|
|
861
|
-
"status": "failed",
|
|
862
|
-
"success": false
|
|
863
|
-
},
|
|
864
|
-
"random_insertion": {
|
|
865
|
-
"status": "failed",
|
|
866
|
-
"success": false
|
|
867
|
-
},
|
|
868
|
-
"reversed_words": {
|
|
869
|
-
"status": "failed",
|
|
870
|
-
"success": false
|
|
871
|
-
},
|
|
872
|
-
"sglue_rte": {
|
|
873
|
-
"status": "failed",
|
|
874
|
-
"success": false
|
|
875
|
-
},
|
|
876
|
-
"stsb": {
|
|
877
|
-
"status": "failed",
|
|
878
|
-
"success": false
|
|
879
|
-
},
|
|
880
|
-
"summarization_gl": {
|
|
881
|
-
"status": "failed",
|
|
882
|
-
"success": false
|
|
883
|
-
},
|
|
884
|
-
"teca": {
|
|
885
|
-
"status": "failed",
|
|
886
|
-
"success": false
|
|
887
|
-
},
|
|
888
|
-
"tinyArc": {
|
|
889
|
-
"status": "failed",
|
|
890
|
-
"success": false
|
|
891
|
-
},
|
|
892
|
-
"tinyGSM8k": {
|
|
893
|
-
"status": "failed",
|
|
894
|
-
"success": false
|
|
895
|
-
},
|
|
896
|
-
"tinyHellaswag": {
|
|
897
|
-
"status": "failed",
|
|
898
|
-
"success": false
|
|
899
|
-
},
|
|
900
|
-
"tinyMMLU": {
|
|
901
|
-
"status": "failed",
|
|
902
|
-
"success": false
|
|
903
|
-
},
|
|
904
|
-
"tinyWinogrande": {
|
|
905
|
-
"status": "failed",
|
|
906
|
-
"success": false
|
|
907
|
-
},
|
|
908
|
-
"unfair_tos": {
|
|
909
|
-
"status": "failed",
|
|
910
|
-
"success": false
|
|
911
|
-
},
|
|
912
|
-
"vaxx_stance": {
|
|
913
|
-
"status": "failed",
|
|
914
|
-
"success": false
|
|
915
|
-
},
|
|
916
|
-
"wiceu": {
|
|
917
|
-
"status": "failed",
|
|
918
|
-
"success": false
|
|
919
|
-
},
|
|
920
|
-
"wmt-ro-en-t5-prompt": {
|
|
921
|
-
"status": "failed",
|
|
922
|
-
"success": false
|
|
923
|
-
},
|
|
924
|
-
"xlsum_es": {
|
|
925
|
-
"status": "failed",
|
|
926
|
-
"success": false
|
|
927
|
-
},
|
|
928
|
-
"xsum": {
|
|
929
|
-
"status": "failed",
|
|
930
|
-
"success": false
|
|
931
|
-
},
|
|
932
|
-
"yahoo_answers_topics": {
|
|
933
|
-
"status": "failed",
|
|
934
|
-
"success": false
|
|
935
|
-
},
|
|
936
|
-
"instructhumaneval": {
|
|
937
|
-
"status": "failed",
|
|
938
|
-
"success": false
|
|
939
|
-
},
|
|
940
|
-
"humanevalpack": {
|
|
941
|
-
"status": "failed",
|
|
942
|
-
"success": false
|
|
943
|
-
}
|
|
944
|
-
}
|
|
945
|
-
}
|