Update README.md

README.md

@@ -1,18 +1,15 @@
 ---
 datasets:
 - nyu-mll/glue
-- super_glue
+- aps/super_glue
 - facebook/anli
 - tasksource/babi_nli
 - sick
 - snli
 - scitail
-- OpenAssistant/oasst1
-- universal_dependencies
 - hans
-- qbao775/PARARULE-Plus
 - alisawuffles/WANLI
-- metaeval/recast
+- tasksource/recast
 - sileod/probability_words_nli
 - joey234/nan-nli
 - pietrolesci/nli_fever
@@ -22,25 +19,17 @@ datasets:
 - pietrolesci/dialogue_nli
 - pietrolesci/mpe
 - pietrolesci/dnc
-- pietrolesci/gpt3_nli
 - pietrolesci/recast_white
 - pietrolesci/joci
-- martn-nguyen/contrast_nli
 - pietrolesci/robust_nli
 - pietrolesci/robust_nli_is_sd
 - pietrolesci/robust_nli_li_ts
 - pietrolesci/gen_debiased_nli
 - pietrolesci/add_one_rte
-- metaeval/imppres
-- pietrolesci/glue_diagnostics
+- tasksource/imppres
 - hlgd
-- PolyAI/banking77
 - paws
-- quora
 - medical_questions_pairs
-- conll2003
-- nlpaueb/finer-139
-- Anthropic/hh-rlhf
 - Anthropic/model-written-evals
 - truthful_qa
 - nightingal3/fig-qa
@@ -63,7 +52,6 @@ datasets:
 - pkavumba/balanced-copa
 - 12ml/e-CARE
 - art
-- tasksource/mmlu
 - winogrande
 - codah
 - ai2_arc
@@ -99,7 +87,6 @@ datasets:
 - sms_spam
 - humicroedit
 - snips_built_in_intents
-- banking77
 - hate_speech_offensive
 - yahoo_answers_topics
 - pacovaldez/stackoverflow-questions
@@ -110,19 +97,13 @@ datasets:
 - allenai/scicite
 - liar
 - relbert/lexical_relation_classification
-- metaeval/linguisticprobing
+- tasksource/linguisticprobing
 - tasksource/crowdflower
 - metaeval/ethics
 - emo
 - google_wellformed_query
 - tweets_hate_speech_detection
 - has_part
-- wnut_17
-- ncbi_disease
-- acronym_identification
-- jnlpba
-- species_800
-- SpeedOfMagic/ontonotes_english
 - blog_authorship_corpus
 - launch/open_question_type
 - health_fact
@@ -141,7 +122,6 @@ datasets:
 - sem_eval_2010_task_8
 - demo-org/auditor_review
 - medmcqa
-- aqua_rat
 - RuyuanWan/Dynasent_Disagreement
 - RuyuanWan/Politeness_Disagreement
 - RuyuanWan/SBIC_Disagreement
@@ -149,93 +129,87 @@ datasets:
 - RuyuanWan/Dilemmas_Disagreement
 - lucasmccabe/logiqa
 - wiki_qa
-- metaeval/cycic_classification
-- metaeval/cycic_multiplechoice
-- metaeval/sts-companion
-- metaeval/commonsense_qa_2.0
-- metaeval/lingnli
-- metaeval/monotonicity-entailment
-- metaeval/arct
-- metaeval/scinli
-- metaeval/naturallogic
+- tasksource/cycic_classification
+- tasksource/cycic_multiplechoice
+- tasksource/sts-companion
+- tasksource/commonsense_qa_2.0
+- tasksource/lingnli
+- tasksource/monotonicity-entailment
+- tasksource/arct
+- tasksource/scinli
+- tasksource/naturallogic
 - onestop_qa
 - demelin/moral_stories
 - corypaik/prost
 - aps/dynahate
 - metaeval/syntactic-augmentation-nli
-- metaeval/autotnli
+- tasksource/autotnli
 - lasha-nlp/CONDAQA
 - openai/webgpt_comparisons
 - Dahoas/synthetic-instruct-gptj-pairwise
 - metaeval/scruples
 - metaeval/wouldyourather
-- sileod/attempto-nli
 - metaeval/defeasible-nli
-- metaeval/help-nli
+- tasksource/help-nli
 - metaeval/nli-veridicality-transitivity
-- metaeval/natural-language-satisfiability
-- metaeval/lonli
+- tasksource/lonli
 - tasksource/dadc-limit-nli
 - ColumbiaNLP/FLUTE
-- metaeval/strategy-qa
+- tasksource/strategy-qa
 - openai/summarize_from_feedback
 - tasksource/folio
-- metaeval/tomi-nli
-- metaeval/avicenna
+- yale-nlp/FOLIO
+- tasksource/tomi-nli
+- tasksource/avicenna
 - stanfordnlp/SHP
 - GBaker/MedQA-USMLE-4-options-hf
-- GBaker/MedQA-USMLE-4-options
 - sileod/wikimedqa
 - declare-lab/cicero
 - amydeng2000/CREAK
-- metaeval/mutual
+- tasksource/mutual
 - inverse-scaling/NeQA
 - inverse-scaling/quote-repetition
 - inverse-scaling/redefine-math
 - tasksource/puzzte
-- metaeval/implicatures
+- tasksource/implicatures
 - race
-- metaeval/spartqa-yn
-- metaeval/spartqa-mchoice
-- metaeval/temporal-nli
-- metaeval/ScienceQA_text_only
-- AndyChiang/cloth
-- metaeval/logiqa-2.0-nli
-- tasksource/oasst1_dense_flat
-- metaeval/boolq-natural-perturbations
-- metaeval/path-naturalness-prediction
+- tasksource/race-c
+- tasksource/spartqa-yn
+- tasksource/spartqa-mchoice
+- tasksource/temporal-nli
 - riddle_sense
+- tasksource/clcd-english
+- maximedb/twentyquestions
+- metaeval/reclor
+- tasksource/counterfactually-augmented-imdb
+- tasksource/counterfactually-augmented-snli
+- metaeval/cnli
+- tasksource/boolq-natural-perturbations
+- metaeval/acceptability-prediction
+- metaeval/equate
+- tasksource/ScienceQA_text_only
 - Jiangjie/ekar_english
-- metaeval/implicit-hate-stg1
+- tasksource/implicit-hate-stg1
 - metaeval/chaos-mnli-ambiguity
 - IlyaGusev/headline_cause
-- metaeval/race-c
-- metaeval/equate
+- tasksource/logiqa-2.0-nli
+- tasksource/oasst2_dense_flat
+- sileod/mindgames
 - metaeval/ambient
-- AndyChiang/dgen
-- metaeval/clcd-english
+- metaeval/path-naturalness-prediction
 - civil_comments
-- metaeval/acceptability-prediction
-- maximedb/twentyquestions
-- metaeval/counterfactually-augmented-snli
+- AndyChiang/cloth
+- AndyChiang/dgen
 - tasksource/I2D2
-- sileod/mindgames
-- metaeval/counterfactually-augmented-imdb
-- metaeval/cnli
-- metaeval/reclor
-- tasksource/oasst1_pairwise_rlhf_reward
-- tasksource/zero-shot-label-nli
 - webis/args_me
 - webis/Touche23-ValueEval
 - tasksource/starcon
-- tasksource/ruletaker
-- lighteval/lsat_qa
+- PolyAI/banking77
 - tasksource/ConTRoL-nli
 - tasksource/tracie
 - tasksource/sherliic
 - tasksource/sen-making
 - tasksource/winowhy
-- mediabiasgroup/mbib-base
 - tasksource/robustLR
 - CLUTRR/v1
 - tasksource/logical-fallacy
@@ -247,15 +221,15 @@ datasets:
 - tasksource/TroFi
 - sharc_modified
 - tasksource/conceptrules_v2
-- tasksource/disrpt
-- conll2000
-- DFKI-SLT/few-nerd
+- metaeval/disrpt
+- tasksource/zero-shot-label-nli
 - tasksource/com2sense
 - tasksource/scone
 - tasksource/winodict
 - tasksource/fool-me-twice
 - tasksource/monli
 - tasksource/corr2cause
+- lighteval/lsat_qa
 - tasksource/apt
 - zeroshot/twitter-financial-news-sentiment
 - tasksource/icl-symbol-tuning-instruct
@@ -263,8 +237,59 @@ datasets:
 - sihaochen/propsegment
 - HannahRoseKirk/HatemojiBuild
 - tasksource/regset
-- tasksource/babi_nli
+- tasksource/esci
 - lmsys/chatbot_arena_conversations
+- neurae/dnd_style_intents
+- hitachi-nlp/FLD.v2
+- tasksource/SDOH-NLI
+- allenai/scifact_entailment
+- tasksource/feasibilityQA
+- tasksource/simple_pair
+- tasksource/AdjectiveScaleProbe-nli
+- tasksource/resnli
+- tasksource/SpaRTUN
+- tasksource/ReSQ
+- tasksource/semantic_fragments_nli
+- MoritzLaurer/dataset_train_nli
+- tasksource/stepgame
+- tasksource/nlgraph
+- tasksource/oasst2_pairwise_rlhf_reward
+- tasksource/hh-rlhf
+- tasksource/ruletaker
+- qbao775/PARARULE-Plus
+- tasksource/proofwriter
+- tasksource/logical-entailment
+- tasksource/nope
+- tasksource/LogicNLI
+- kiddothe2b/contract-nli
+- AshtonIsNotHere/nli4ct_semeval2024
+- tasksource/lsat-ar
+- tasksource/lsat-rc
+- AshtonIsNotHere/biosift-nli
+- tasksource/brainteasers
+- Anthropic/persuasion
+- erbacher/AmbigNQ-clarifying-question
+- tasksource/SIGA-nli
+- unigram/FOL-nli
+- tasksource/goal-step-wikihow
+- GGLab/PARADISE
+- tasksource/doc-nli
+- tasksource/mctest-nli
+- tasksource/patent-phrase-similarity
+- tasksource/natural-language-satisfiability
+- tasksource/idioms-nli
+- tasksource/lifecycle-entailment
+- nvidia/HelpSteer
+- nvidia/HelpSteer2
+- sadat2307/MSciNLI
+- pushpdeep/UltraFeedback-paired
+- tasksource/AES2-essay-scoring
+- tasksource/english-grading
+- tasksource/wice
+- Dzeniks/hover
+- sileod/missing-item-prediction
+- tasksource/tasksource_dpo_pairs
+
 language: en
 library_name: transformers
 license: apache-2.0