Updated model

README.md

@@ -1,3 +1,382 @@
 ---
 license: apache-2.0
+language: en
+tags:
+- deberta-v3-base
+- deberta-v3
+- deberta
+- text-classification
+- nli
+- natural-language-inference
+- multitask
+- multi-task
+- pipeline
+- extreme-multi-task
+- extreme-mtl
+- tasksource
+- zero-shot
+- rlhf
+model-index:
+- name: deberta-v3-base-tasksource-nli
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: glue
+      type: glue
+      config: rte
+      split: validation
+    metrics:
+    - type: accuracy
+      value: 0.89
+  - task:
+      type: natural-language-inference
+      name: Natural Language Inference
+    dataset:
+      name: anli-r3
+      type: anli
+      config: plain_text
+      split: validation
+    metrics:
+      - type: accuracy
+        value: 0.52
+        name: Accuracy
+datasets:
+- glue
+- super_glue
+- anli
+- tasksource/babi_nli
+- sick
+- snli
+- scitail
+- OpenAssistant/oasst1
+- universal_dependencies
+- hans
+- qbao775/PARARULE-Plus
+- alisawuffles/WANLI
+- metaeval/recast
+- sileod/probability_words_nli
+- joey234/nan-nli
+- pietrolesci/nli_fever
+- pietrolesci/breaking_nli
+- pietrolesci/conj_nli
+- pietrolesci/fracas
+- 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
+- hlgd
+- PolyAI/banking77
+- paws
+- quora
+- medical_questions_pairs
+- conll2003
+- nlpaueb/finer-139
+- Anthropic/hh-rlhf
+- Anthropic/model-written-evals
+- truthful_qa
+- nightingal3/fig-qa
+- tasksource/bigbench
+- blimp
+- cos_e
+- cosmos_qa
+- dream
+- openbookqa
+- qasc
+- quartz
+- quail
+- head_qa
+- sciq
+- social_i_qa
+- wiki_hop
+- wiqa
+- piqa
+- hellaswag
+- pkavumba/balanced-copa
+- 12ml/e-CARE
+- art
+- tasksource/mmlu
+- winogrande
+- codah
+- ai2_arc
+- definite_pronoun_resolution
+- swag
+- math_qa
+- metaeval/utilitarianism
+- mteb/amazon_counterfactual
+- SetFit/insincere-questions
+- SetFit/toxic_conversations
+- turingbench/TuringBench
+- trec
+- tals/vitaminc
+- hope_edi
+- strombergnlp/rumoureval_2019
+- ethos
+- tweet_eval
+- discovery
+- pragmeval
+- silicone
+- lex_glue
+- papluca/language-identification
+- imdb
+- rotten_tomatoes
+- ag_news
+- yelp_review_full
+- financial_phrasebank
+- poem_sentiment
+- dbpedia_14
+- amazon_polarity
+- app_reviews
+- hate_speech18
+- sms_spam
+- humicroedit
+- snips_built_in_intents
+- banking77
+- hate_speech_offensive
+- yahoo_answers_topics
+- pacovaldez/stackoverflow-questions
+- zapsdcn/hyperpartisan_news
+- zapsdcn/sciie
+- zapsdcn/citation_intent
+- go_emotions
+- allenai/scicite
+- liar
+- relbert/lexical_relation_classification
+- metaeval/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
+- commonsense_qa
+- mc_taco
+- ade_corpus_v2
+- prajjwal1/discosense
+- circa
+- PiC/phrase_similarity
+- copenlu/scientific-exaggeration-detection
+- quarel
+- mwong/fever-evidence-related
+- numer_sense
+- dynabench/dynasent
+- raquiba/Sarcasm_News_Headline
+- sem_eval_2010_task_8
+- demo-org/auditor_review
+- medmcqa
+- aqua_rat
+- RuyuanWan/Dynasent_Disagreement
+- RuyuanWan/Politeness_Disagreement
+- RuyuanWan/SBIC_Disagreement
+- RuyuanWan/SChem_Disagreement
+- 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
+- onestop_qa
+- demelin/moral_stories
+- corypaik/prost
+- aps/dynahate
+- metaeval/syntactic-augmentation-nli
+- metaeval/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
+- metaeval/nli-veridicality-transitivity
+- metaeval/natural-language-satisfiability
+- metaeval/lonli
+- tasksource/dadc-limit-nli
+- ColumbiaNLP/FLUTE
+- metaeval/strategy-qa
+- openai/summarize_from_feedback
+- tasksource/folio
+- metaeval/tomi-nli
+- metaeval/avicenna
+- stanfordnlp/SHP
+- GBaker/MedQA-USMLE-4-options-hf
+- GBaker/MedQA-USMLE-4-options
+- sileod/wikimedqa
+- declare-lab/cicero
+- amydeng2000/CREAK
+- metaeval/mutual
+- inverse-scaling/NeQA
+- inverse-scaling/quote-repetition
+- inverse-scaling/redefine-math
+- tasksource/puzzte
+- metaeval/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
+- riddle_sense
+- Jiangjie/ekar_english
+- metaeval/implicit-hate-stg1
+- metaeval/chaos-mnli-ambiguity
+- IlyaGusev/headline_cause
+- metaeval/race-c
+- metaeval/equate
+- metaeval/ambient
+- AndyChiang/dgen
+- metaeval/clcd-english
+- civil_comments
+- metaeval/acceptability-prediction
+- maximedb/twentyquestions
+- metaeval/counterfactually-augmented-snli
+- 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
+- tasksource/ConTRoL-nli
+- tasksource/tracie
+- tasksource/sherliic
+- tasksource/sen-making
+- tasksource/winowhy
+- mediabiasgroup/mbib-base
+- tasksource/robustLR
+- CLUTRR/v1
+- tasksource/logical-fallacy
+- tasksource/parade
+- tasksource/cladder
+- tasksource/subjectivity
+- tasksource/MOH
+- tasksource/VUAC
+- tasksource/TroFi
+- sharc_modified
+- tasksource/conceptrules_v2
+- tasksource/disrpt
+- conll2000
+- DFKI-SLT/few-nerd
+- tasksource/com2sense
+- tasksource/scone
+- tasksource/winodict
+- tasksource/fool-me-twice
+- tasksource/monli
+- tasksource/corr2cause
+- tasksource/apt
+- zeroshot/twitter-financial-news-sentiment
+- tasksource/icl-symbol-tuning-instruct
+- tasksource/SpaceNLI
+- sihaochen/propsegment
+- HannahRoseKirk/HatemojiBuild
+- tasksource/regset
+- tasksource/babi_nli
+- lmsys/chatbot_arena_conversations
+metrics:
+- accuracy
+library_name: transformers
+pipeline_tag: zero-shot-classification
 ---
+
+# Model Card for DeBERTa-v3-base-tasksource-nli
+
+This is [DeBERTa-v3-base](https://hf.co/microsoft/deberta-v3-base) fine-tuned with multi-task learning on 600 tasks of the [tasksource collection](https://github.com/sileod/tasksource/).
+This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for:
+- Zero-shot entailment-based classification pipeline (similar to bart-mnli), see [ZS].
+- Natural language inference, and many other tasks with tasksource-adapters, see [TA]
+- Further fine-tuning with a new task (classification, token classification or multiple-choice).
+
+# [ZS] Zero-shot classification pipeline
+```python
+from transformers import pipeline
+classifier = pipeline("zero-shot-classification",model="sileod/deberta-v3-base-tasksource-nli")
+
+text = "one day I will see the world"
+candidate_labels = ['travel', 'cooking', 'dancing']
+classifier(text, candidate_labels)
+```
+NLI training data of this model includes [label-nli](https://huggingface.co/datasets/tasksource/zero-shot-label-nli), a NLI dataset specially constructed to improve this kind of zero-shot classification.
+
+# [TA] Tasksource-adapters: 1 line access to hundreds of tasks 
+
+```python
+!pip install tasknet tasksource
+import tasknet as tn
+pipe = tn.load_pipeline('sileod/deberta-v3-base-tasksource-nli','glue/sst2') # works for 500+ tasksource tasks
+pipe(['That movie was great !', 'Awful movie.'])
+# [{'label': 'positive', 'score': 0.9956}, {'label': 'negative', 'score': 0.9967}]
+```
+The list of tasks is available in model config.json.
+This is more efficient than ZS since it requires only one forward pass per example, but it is less flexible.
+
+
+## Evaluation
+This model ranked 1st among all models with the microsoft/deberta-v3-base architecture according to the IBM model recycling evaluation.
+https://ibm.github.io/model-recycling/
+
+### Software and training details
+
+The model was trained on 600 tasks for 200k steps with a batch size of 384 and a peak learning rate of 2e-5. Training took 12 days on Nvidia A30 24GB gpu.
+This is the shared model with the MNLI classifier on top. Each task had a specific CLS embedding, which is dropped 10% of the time to facilitate model use without it. All multiple-choice model used the same classification layers. For classification tasks, models shared weights if their labels matched.
+
+
+https://github.com/sileod/tasksource/ \
+https://github.com/sileod/tasknet/ \
+Training code: https://colab.research.google.com/drive/1iB4Oxl9_B5W3ZDzXoWJN-olUbqLBxgQS?usp=sharing
+
+# Citation
+
+More details on this [article:](https://arxiv.org/abs/2301.05948) 
+```
+@article{sileo2023tasksource,
+  title={tasksource: Structured Dataset Preprocessing Annotations for Frictionless Extreme Multi-Task Learning and Evaluation},
+  author={Sileo, Damien},
+  url= {https://arxiv.org/abs/2301.05948},
+  journal={arXiv preprint arXiv:2301.05948},
+  year={2023}
+}
+```
+
+
+# Model Card Contact
+
+damien.sileo@inria.fr
+
+
+</details>

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,1039 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifiers_size": [
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    1,
+    2,
+    3,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    1,
+    3,
+    3,
+    2,
+    2,
+    3,
+    2,
+    6,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    2,
+    5,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2,
+    2,
+    2,
+    47,
+    23,
+    9,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    20,
+    50,
+    3,
+    3,
+    4,
+    2,
+    8,
+    3,
+    3,
+    3,
+    3,
+    20,
+    3,
+    2,
+    2,
+    2,
+    4,
+    3,
+    174,
+    2,
+    2,
+    2,
+    2,
+    2,
+    41,
+    51,
+    3,
+    2,
+    3,
+    17,
+    18,
+    2,
+    8,
+    2,
+    2,
+    2,
+    2,
+    3,
+    16,
+    11,
+    3,
+    42,
+    3,
+    7,
+    12,
+    7,
+    4,
+    100,
+    13,
+    100,
+    8,
+    1,
+    20,
+    2,
+    2,
+    4,
+    5,
+    3,
+    4,
+    14,
+    2,
+    6,
+    4,
+    2,
+    1,
+    3,
+    10,
+    3,
+    10,
+    4,
+    2,
+    7,
+    6,
+    28,
+    3,
+    6,
+    4,
+    5,
+    6,
+    3,
+    7,
+    2,
+    20,
+    2,
+    2,
+    7,
+    2,
+    6,
+    2,
+    2,
+    2,
+    13,
+    3,
+    4,
+    3,
+    2,
+    4,
+    2,
+    9,
+    2,
+    2,
+    2,
+    2,
+    4,
+    1,
+    2,
+    1,
+    13,
+    3,
+    5,
+    11,
+    37,
+    2,
+    49,
+    12,
+    40,
+    10,
+    4,
+    1,
+    2,
+    2,
+    1,
+    5,
+    2,
+    3,
+    2,
+    2,
+    12,
+    3,
+    3,
+    2,
+    19,
+    3,
+    1,
+    2,
+    2,
+    2,
+    2,
+    2,
+    1,
+    2,
+    2,
+    1,
+    1,
+    2,
+    3,
+    2,
+    1,
+    4,
+    4,
+    1,
+    1,
+    1,
+    2,
+    3,
+    2,
+    3,
+    1,
+    1,
+    2,
+    1,
+    3,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    2,
+    2,
+    2,
+    1,
+    3,
+    2,
+    2,
+    1,
+    1,
+    1,
+    1,
+    2,
+    1,
+    1,
+    1,
+    1,
+    4,
+    1,
+    1,
+    1,
+    1,
+    3,
+    1,
+    3,
+    1,
+    2,
+    2,
+    1,
+    2,
+    3,
+    3,
+    2,
+    1,
+    3,
+    1,
+    1,
+    3,
+    1,
+    3,
+    2,
+    1,
+    1,
+    1,
+    2,
+    2,
+    50,
+    50,
+    50,
+    50,
+    2,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    77,
+    2,
+    1,
+    3,
+    2,
+    2,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    18,
+    13,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    4,
+    2,
+    24,
+    23,
+    67,
+    279,
+    3,
+    2,
+    2,
+    1,
+    2,
+    2,
+    3,
+    1,
+    2,
+    3,
+    2,
+    3,
+    3,
+    2,
+    2,
+    4,
+    1,
+    17,
+    2,
+    3,
+    3,
+    3,
+    1,
+    1
+  ],
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "tasks": [
+    "glue/mnli",
+    "glue/qnli",
+    "glue/rte",
+    "glue/wnli",
+    "glue/mrpc",
+    "glue/qqp",
+    "glue/stsb",
+    "super_glue/boolq",
+    "super_glue/cb",
+    "super_glue/multirc",
+    "super_glue/wic",
+    "super_glue/axg",
+    "anli/a1",
+    "anli/a2",
+    "anli/a3",
+    "sick/label",
+    "sick/relatedness",
+    "sick/entailment_AB",
+    "snli",
+    "scitail/snli_format",
+    "hans",
+    "WANLI",
+    "recast/recast_factuality",
+    "recast/recast_kg_relations",
+    "recast/recast_puns",
+    "recast/recast_sentiment",
+    "recast/recast_verbnet",
+    "recast/recast_ner",
+    "recast/recast_verbcorner",
+    "recast/recast_megaveridicality",
+    "probability_words_nli/reasoning_2hop",
+    "probability_words_nli/usnli",
+    "probability_words_nli/reasoning_1hop",
+    "nan-nli/joey234--nan-nli",
+    "nli_fever",
+    "breaking_nli",
+    "conj_nli",
+    "fracas",
+    "dialogue_nli",
+    "mpe",
+    "dnc",
+    "recast_white/fnplus",
+    "recast_white/sprl",
+    "recast_white/dpr",
+    "joci",
+    "robust_nli/IS_CS",
+    "robust_nli/LI_LI",
+    "robust_nli/ST_WO",
+    "robust_nli/PI_SP",
+    "robust_nli/PI_CD",
+    "robust_nli/ST_SE",
+    "robust_nli/ST_NE",
+    "robust_nli/ST_LM",
+    "robust_nli_is_sd",
+    "robust_nli_li_ts",
+    "add_one_rte",
+    "imppres/implicature_numerals_2_3/log",
+    "imppres/implicature_modals/log",
+    "imppres/implicature_gradable_verb/log",
+    "imppres/implicature_gradable_adjective/log",
+    "imppres/implicature_connectives/log",
+    "imppres/implicature_numerals_10_100/log",
+    "imppres/implicature_quantifiers/log",
+    "glue_diagnostics/diagnostics",
+    "hlgd",
+    "paws/labeled_final",
+    "paws/labeled_swap",
+    "medical_questions_pairs",
+    "conll2003/pos_tags",
+    "conll2003/chunk_tags",
+    "conll2003/ner_tags",
+    "hh-rlhf",
+    "model-written-evals",
+    "truthful_qa/multiple_choice",
+    "fig-qa",
+    "bigbench/analytic_entailment",
+    "bigbench/figure_of_speech_detection",
+    "bigbench/riddle_sense",
+    "bigbench/physical_intuition",
+    "bigbench/metaphor_boolean",
+    "bigbench/epistemic_reasoning",
+    "bigbench/dark_humor_detection",
+    "bigbench/international_phonetic_alphabet_nli",
+    "bigbench/arithmetic",
+    "bigbench/cifar10_classification",
+    "bigbench/hhh_alignment",
+    "bigbench/strategyqa",
+    "bigbench/play_dialog_same_or_different",
+    "bigbench/odd_one_out",
+    "bigbench/undo_permutation",
+    "bigbench/key_value_maps",
+    "bigbench/empirical_judgments",
+    "bigbench/question_selection",
+    "bigbench/date_understanding",
+    "bigbench/vitaminc_fact_verification",
+    "bigbench/cause_and_effect",
+    "bigbench/known_unknowns",
+    "bigbench/causal_judgment",
+    "bigbench/nonsense_words_grammar",
+    "bigbench/movie_dialog_same_or_different",
+    "bigbench/unit_interpretation",
+    "bigbench/abstract_narrative_understanding",
+    "bigbench/dyck_languages",
+    "bigbench/elementary_math_qa",
+    "bigbench/identify_math_theorems",
+    "bigbench/misconceptions",
+    "bigbench/crash_blossom",
+    "bigbench/novel_concepts",
+    "bigbench/social_iqa",
+    "bigbench/hindu_knowledge",
+    "bigbench/anachronisms",
+    "bigbench/cs_algorithms",
+    "bigbench/ruin_names",
+    "bigbench/phrase_relatedness",
+    "bigbench/crass_ai",
+    "bigbench/conceptual_combinations",
+    "bigbench/discourse_marker_prediction",
+    "bigbench/logic_grid_puzzle",
+    "bigbench/navigate",
+    "bigbench/emoji_movie",
+    "bigbench/implicit_relations",
+    "bigbench/presuppositions_as_nli",
+    "bigbench/code_line_description",
+    "bigbench/color",
+    "bigbench/gre_reading_comprehension",
+    "bigbench/physics",
+    "bigbench/symbol_interpretation",
+    "bigbench/tracking_shuffled_objects",
+    "bigbench/entailed_polarity",
+    "bigbench/mathematical_induction",
+    "bigbench/metaphor_understanding",
+    "bigbench/movie_recommendation",
+    "bigbench/simple_ethical_questions",
+    "bigbench/hyperbaton",
+    "bigbench/english_proverbs",
+    "bigbench/similarities_abstraction",
+    "bigbench/emojis_emotion_prediction",
+    "bigbench/temporal_sequences",
+    "bigbench/human_organs_senses",
+    "bigbench/penguins_in_a_table",
+    "bigbench/winowhy",
+    "bigbench/authorship_verification",
+    "bigbench/sentence_ambiguity",
+    "bigbench/mnist_ascii",
+    "bigbench/identify_odd_metaphor",
+    "bigbench/geometric_shapes",
+    "bigbench/evaluating_information_essentiality",
+    "bigbench/timedial",
+    "bigbench/salient_translation_error_detection",
+    "bigbench/suicide_risk",
+    "bigbench/fantasy_reasoning",
+    "bigbench/implicatures",
+    "bigbench/logical_sequence",
+    "bigbench/irony_identification",
+    "bigbench/formal_fallacies_syllogisms_negation",
+    "bigbench/understanding_fables",
+    "bigbench/logical_args",
+    "bigbench/analogical_similarity",
+    "bigbench/social_support",
+    "bigbench/logical_fallacy_detection",
+    "bigbench/bbq_lite_json",
+    "bigbench/reasoning_about_colored_objects",
+    "bigbench/intent_recognition",
+    "bigbench/contextual_parametric_knowledge_conflicts",
+    "bigbench/general_knowledge",
+    "bigbench/strange_stories",
+    "bigbench/sports_understanding",
+    "bigbench/checkmate_in_one",
+    "bigbench/moral_permissibility",
+    "bigbench/goal_step_wikihow",
+    "bigbench/snarks",
+    "bigbench/disambiguation_qa",
+    "bigbench/real_or_fake_text",
+    "bigbench/logical_deduction",
+    "bigbench/fact_checker",
+    "cos_e/v1.0",
+    "cosmos_qa",
+    "dream",
+    "openbookqa",
+    "qasc",
+    "quartz",
+    "quail",
+    "head_qa/en",
+    "sciq",
+    "social_i_qa",
+    "wiki_hop/original",
+    "wiqa",
+    "piqa",
+    "hellaswag",
+    "super_glue/copa",
+    "balanced-copa",
+    "e-CARE",
+    "art",
+    "winogrande/winogrande_xl",
+    "codah/codah",
+    "ai2_arc/ARC-Challenge/challenge",
+    "ai2_arc/ARC-Easy/challenge",
+    "definite_pronoun_resolution",
+    "swag/regular",
+    "math_qa",
+    "glue/cola",
+    "glue/sst2",
+    "utilitarianism",
+    "amazon_counterfactual/en",
+    "insincere-questions",
+    "toxic_conversations",
+    "TuringBench",
+    "trec",
+    "vitaminc/tals--vitaminc",
+    "hope_edi/english",
+    "rumoureval_2019/RumourEval2019",
+    "ethos/binary",
+    "ethos/multilabel",
+    "tweet_eval/stance_hillary",
+    "tweet_eval/stance_feminist",
+    "tweet_eval/stance_climate",
+    "tweet_eval/stance_atheism",
+    "tweet_eval/emoji",
+    "tweet_eval/sentiment",
+    "tweet_eval/offensive",
+    "tweet_eval/irony",
+    "tweet_eval/hate",
+    "tweet_eval/emotion",
+    "tweet_eval/stance_abortion",
+    "discovery/discovery",
+    "pragmeval/squinky-formality",
+    "pragmeval/squinky-implicature",
+    "pragmeval/emobank-dominance",
+    "pragmeval/squinky-informativeness",
+    "pragmeval/emobank-arousal",
+    "pragmeval/switchboard",
+    "pragmeval/mrda",
+    "pragmeval/verifiability",
+    "pragmeval/emobank-valence",
+    "pragmeval/emergent",
+    "pragmeval/gum",
+    "pragmeval/stac",
+    "pragmeval/persuasiveness-eloquence",
+    "pragmeval/persuasiveness-premisetype",
+    "pragmeval/persuasiveness-relevance",
+    "pragmeval/persuasiveness-specificity",
+    "pragmeval/persuasiveness-strength",
+    "pragmeval/sarcasm",
+    "pragmeval/persuasiveness-claimtype",
+    "pragmeval/pdtb",
+    "silicone/iemocap",
+    "silicone/sem",
+    "silicone/oasis",
+    "silicone/meld_s",
+    "silicone/meld_e",
+    "silicone/maptask",
+    "silicone/dyda_e",
+    "silicone/dyda_da",
+    "lex_glue/eurlex",
+    "lex_glue/scotus",
+    "lex_glue/ledgar",
+    "lex_glue/unfair_tos",
+    "lex_glue/case_hold",
+    "language-identification",
+    "imdb",
+    "rotten_tomatoes",
+    "ag_news",
+    "yelp_review_full/yelp_review_full",
+    "financial_phrasebank/sentences_allagree",
+    "poem_sentiment",
+    "dbpedia_14/dbpedia_14",
+    "amazon_polarity/amazon_polarity",
+    "app_reviews",
+    "hate_speech18",
+    "sms_spam",
+    "humicroedit/subtask-1",
+    "humicroedit/subtask-2",
+    "snips_built_in_intents",
+    "hate_speech_offensive",
+    "yahoo_answers_topics",
+    "stackoverflow-questions",
+    "hyperpartisan_news",
+    "sciie",
+    "citation_intent",
+    "go_emotions/simplified",
+    "scicite",
+    "liar",
+    "lexical_relation_classification/K&H+N",
+    "lexical_relation_classification/CogALexV",
+    "lexical_relation_classification/BLESS",
+    "lexical_relation_classification/ROOT09",
+    "lexical_relation_classification/EVALution",
+    "linguisticprobing/bigram_shift",
+    "linguisticprobing/top_constituents",
+    "linguisticprobing/subj_number",
+    "linguisticprobing/odd_man_out",
+    "linguisticprobing/tree_depth",
+    "linguisticprobing/past_present",
+    "linguisticprobing/sentence_length",
+    "linguisticprobing/obj_number",
+    "linguisticprobing/coordination_inversion",
+    "crowdflower/political-media-audience",
+    "crowdflower/text_emotion",
+    "crowdflower/economic-news",
+    "crowdflower/corporate-messaging",
+    "crowdflower/airline-sentiment",
+    "crowdflower/tweet_global_warming",
+    "crowdflower/sentiment_nuclear_power",
+    "crowdflower/political-media-bias",
+    "crowdflower/political-media-message",
+    "ethics/commonsense",
+    "ethics/deontology",
+    "ethics/justice",
+    "ethics/virtue",
+    "emo/emo2019",
+    "google_wellformed_query",
+    "tweets_hate_speech_detection",
+    "has_part",
+    "wnut_17/wnut_17",
+    "ncbi_disease/ncbi_disease",
+    "acronym_identification",
+    "jnlpba/jnlpba",
+    "ontonotes_english/SpeedOfMagic--ontonotes_english",
+    "blog_authorship_corpus/gender",
+    "blog_authorship_corpus/age",
+    "blog_authorship_corpus/horoscope",
+    "blog_authorship_corpus/job",
+    "open_question_type",
+    "health_fact",
+    "commonsense_qa",
+    "mc_taco",
+    "ade_corpus_v2/Ade_corpus_v2_classification",
+    "discosense",
+    "circa",
+    "phrase_similarity",
+    "scientific-exaggeration-detection",
+    "quarel",
+    "fever-evidence-related/mwong--fever-related",
+    "numer_sense",
+    "dynasent/dynabench.dynasent.r1.all/r1",
+    "dynasent/dynabench.dynasent.r2.all/r2",
+    "Sarcasm_News_Headline",
+    "sem_eval_2010_task_8",
+    "auditor_review/demo-org--auditor_review",
+    "medmcqa",
+    "Dynasent_Disagreement",
+    "Politeness_Disagreement",
+    "SBIC_Disagreement",
+    "SChem_Disagreement",
+    "Dilemmas_Disagreement",
+    "logiqa",
+    "wiki_qa",
+    "cycic_classification",
+    "cycic_multiplechoice",
+    "sts-companion",
+    "commonsense_qa_2.0",
+    "lingnli",
+    "monotonicity-entailment",
+    "arct",
+    "scinli",
+    "naturallogic",
+    "onestop_qa",
+    "moral_stories/full",
+    "prost",
+    "dynahate",
+    "syntactic-augmentation-nli",
+    "autotnli",
+    "CONDAQA",
+    "webgpt_comparisons",
+    "synthetic-instruct-gptj-pairwise",
+    "scruples",
+    "wouldyourather",
+    "attempto-nli",
+    "defeasible-nli/atomic",
+    "defeasible-nli/snli",
+    "help-nli",
+    "nli-veridicality-transitivity",
+    "natural-language-satisfiability",
+    "lonli",
+    "dadc-limit-nli",
+    "FLUTE",
+    "strategy-qa",
+    "summarize_from_feedback/comparisons",
+    "folio",
+    "tomi-nli",
+    "avicenna",
+    "SHP",
+    "MedQA-USMLE-4-options-hf",
+    "wikimedqa/medwiki",
+    "cicero",
+    "CREAK",
+    "mutual",
+    "NeQA",
+    "quote-repetition",
+    "redefine-math",
+    "puzzte",
+    "implicatures",
+    "race/middle",
+    "race/high",
+    "race-c",
+    "spartqa-yn",
+    "spartqa-mchoice",
+    "temporal-nli",
+    "riddle_sense",
+    "clcd-english",
+    "twentyquestions",
+    "reclor",
+    "counterfactually-augmented-imdb",
+    "counterfactually-augmented-snli",
+    "cnli",
+    "boolq-natural-perturbations",
+    "acceptability-prediction",
+    "equate",
+    "ScienceQA_text_only",
+    "ekar_english",
+    "implicit-hate-stg1",
+    "chaos-mnli-ambiguity",
+    "headline_cause/en_simple",
+    "logiqa-2.0-nli",
+    "oasst1_dense_flat/quality",
+    "oasst1_dense_flat/toxicity",
+    "oasst1_dense_flat/helpfulness",
+    "PARARULE-Plus",
+    "mindgames",
+    "universal_dependencies/en_ewt/deprel",
+    "universal_dependencies/en_lines/deprel",
+    "universal_dependencies/en_partut/deprel",
+    "universal_dependencies/en_gum/deprel",
+    "ambient",
+    "path-naturalness-prediction",
+    "civil_comments/toxicity",
+    "civil_comments/severe_toxicity",
+    "civil_comments/obscene",
+    "civil_comments/threat",
+    "civil_comments/insult",
+    "civil_comments/identity_attack",
+    "civil_comments/sexual_explicit",
+    "cloth",
+    "dgen",
+    "oasst1_pairwise_rlhf_reward",
+    "I2D2",
+    "args_me",
+    "Touche23-ValueEval",
+    "starcon",
+    "banking77",
+    "ruletaker",
+    "lsat_qa/all",
+    "ConTRoL-nli",
+    "tracie",
+    "sherliic",
+    "sen-making/1",
+    "sen-making/2",
+    "winowhy",
+    "mbib-base/cognitive-bias",
+    "mbib-base/fake-news",
+    "mbib-base/gender-bias",
+    "mbib-base/hate-speech",
+    "mbib-base/linguistic-bias",
+    "mbib-base/political-bias",
+    "mbib-base/racial-bias",
+    "mbib-base/text-level-bias",
+    "robustLR",
+    "v1/gen_train234_test2to10",
+    "logical-fallacy",
+    "parade",
+    "cladder",
+    "subjectivity",
+    "MOH",
+    "VUAC",
+    "TroFi",
+    "sharc_modified/mod",
+    "conceptrules_v2",
+    "disrpt/eng.dep.scidtb",
+    "conll2000",
+    "few-nerd/supervised",
+    "finer-139",
+    "zero-shot-label-nli",
+    "com2sense",
+    "scone",
+    "winodict",
+    "fool-me-twice",
+    "monli",
+    "corr2cause",
+    "lsat_qa/all",
+    "apt",
+    "twitter-financial-news-sentiment",
+    "icl-symbol-tuning-instruct",
+    "SpaceNLI",
+    "propsegment/nli",
+    "HatemojiBuild",
+    "regset",
+    "esci",
+    "chatbot_arena_conversations",
+    "dnd_style_intents",
+    "babi_nli",
+    "gen_debiased_nli",
+    "imppres/presupposition",
+    "/prag",
+    "blimp-2",
+    "mmlu-4"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

gitattributes.txt

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58b81ba665995176104a66f7b7d0b9e2e412564f6b33917e84c4eb920946841
+size 737726552

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e28518532d77001e5030110c5761ec75499fc5fad1a7e81045c7ce0ba0a86e3
+size 737771833

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tasks.md

@@ -0,0 +1,444 @@
+- 0 babi_nli/counting
+- 1 babi_nli/indefinite-knowledge
+- 2 babi_nli/simple-negation
+- 3 babi_nli/three-arg-relations
+- 4 babi_nli/basic-induction
+- 5 babi_nli/time-reasoning
+- 6 babi_nli/compound-coreference
+- 7 babi_nli/path-finding
+- 8 babi_nli/positional-reasoning
+- 9 babi_nli/conjunction
+- 10 babi_nli/size-reasoning
+- 11 babi_nli/yes-no-questions
+- 12 babi_nli/basic-coreference
+- 13 babi_nli/two-supporting-facts
+- 14 babi_nli/lists-sets
+- 15 babi_nli/two-arg-relations
+- 16 babi_nli/three-supporting-facts
+- 17 babi_nli/basic-deduction
+- 18 babi_nli/single-supporting-fact
+- 19 anli/a1
+- 20 anli/a2
+- 21 anli/a3
+- 22 sick/label
+- 23 sick/relatedness
+- 24 sick/entailment_AB
+- 25 sick/entailment_BA
+- 26 snli
+- 27 scitail/snli_format
+- 28 hans
+- 29 WANLI
+- 30 recast/recast_kg_relations
+- 31 recast/recast_puns
+- 32 recast/recast_factuality
+- 33 recast/recast_megaveridicality
+- 34 recast/recast_verbcorner
+- 35 recast/recast_verbnet
+- 36 recast/recast_ner
+- 37 recast/recast_sentiment
+- 38 probability_words_nli/usnli
+- 39 probability_words_nli/reasoning_1hop
+- 40 probability_words_nli/reasoning_2hop
+- 41 nan-nli/joey234--nan-nli
+- 42 nli_fever
+- 43 breaking_nli
+- 44 conj_nli
+- 45 fracas
+- 46 dialogue_nli
+- 47 mpe
+- 48 dnc
+- 49 gpt3_nli
+- 50 recast_white/fnplus
+- 51 recast_white/sprl
+- 52 recast_white/dpr
+- 53 joci
+- 54 contrast_nli
+- 55 robust_nli/IS_CS
+- 56 robust_nli/LI_LI
+- 57 robust_nli/ST_WO
+- 58 robust_nli/PI_SP
+- 59 robust_nli/PI_CD
+- 60 robust_nli/ST_SE
+- 61 robust_nli/ST_NE
+- 62 robust_nli/ST_LM
+- 63 robust_nli_is_sd
+- 64 robust_nli_li_ts
+- 65 gen_debiased_nli/snli_seq_z
+- 66 gen_debiased_nli/snli_z_aug
+- 67 gen_debiased_nli/snli_par_z
+- 68 gen_debiased_nli/mnli_par_z
+- 69 gen_debiased_nli/mnli_z_aug
+- 70 gen_debiased_nli/mnli_seq_z
+- 71 add_one_rte
+- 72 imppres/presupposition_cleft_uniqueness/presupposition
+- 73 imppres/presupposition_possessed_definites_uniqueness/presupposition
+- 74 imppres/presupposition_possessed_definites_existence/presupposition
+- 75 imppres/presupposition_only_presupposition/presupposition
+- 76 imppres/presupposition_all_n_presupposition/presupposition
+- 77 imppres/presupposition_both_presupposition/presupposition
+- 78 imppres/presupposition_change_of_state/presupposition
+- 79 imppres/presupposition_cleft_existence/presupposition
+- 80 imppres/presupposition_question_presupposition/presupposition
+- 81 imppres/implicature_modals/prag
+- 82 imppres/implicature_numerals_10_100/prag
+- 83 imppres/implicature_numerals_2_3/prag
+- 84 imppres/implicature_gradable_adjective/prag
+- 85 imppres/implicature_quantifiers/prag
+- 86 imppres/implicature_gradable_verb/prag
+- 87 imppres/implicature_connectives/prag
+- 88 imppres/implicature_gradable_adjective/log
+- 89 imppres/implicature_gradable_verb/log
+- 90 imppres/implicature_numerals_2_3/log
+- 91 imppres/implicature_numerals_10_100/log
+- 92 imppres/implicature_modals/log
+- 93 imppres/implicature_quantifiers/log
+- 94 imppres/implicature_connectives/log
+- 95 glue_diagnostics/diagnostics
+- 96 hlgd
+- 97 paws/labeled_final
+- 98 paws/labeled_swap
+- 99 quora
+- 100 medical_questions_pairs
+- 101 conll2003/pos_tags
+- 102 conll2003/chunk_tags
+- 103 conll2003/ner_tags
+- 104 hh-rlhf
+- 105 model-written-evals
+- 106 truthful_qa/multiple_choice
+- 107 fig-qa
+- 108 bigbench/fantasy_reasoning
+- 109 bigbench/nonsense_words_grammar
+- 110 bigbench/analytic_entailment
+- 111 bigbench/logic_grid_puzzle
+- 112 bigbench/geometric_shapes
+- 113 bigbench/key_value_maps
+- 114 bigbench/analogical_similarity
+- 115 bigbench/metaphor_understanding
+- 116 bigbench/metaphor_boolean
+- 117 bigbench/ruin_names
+- 118 bigbench/cs_algorithms
+- 119 bigbench/physical_intuition
+- 120 bigbench/mnist_ascii
+- 121 bigbench/moral_permissibility
+- 122 bigbench/emoji_movie
+- 123 bigbench/snarks
+- 124 bigbench/timedial
+- 125 bigbench/dark_humor_detection
+- 126 bigbench/gre_reading_comprehension
+- 127 bigbench/empirical_judgments
+- 128 bigbench/causal_judgment
+- 129 bigbench/fact_checker
+- 130 bigbench/logical_fallacy_detection
+- 131 bigbench/identify_math_theorems
+- 132 bigbench/dyck_languages
+- 133 bigbench/winowhy
+- 134 bigbench/logical_sequence
+- 135 bigbench/strategyqa
+- 136 bigbench/unit_interpretation
+- 137 bigbench/authorship_verification
+- 138 bigbench/undo_permutation
+- 139 bigbench/epistemic_reasoning
+- 140 bigbench/human_organs_senses
+- 141 bigbench/misconceptions
+- 142 bigbench/international_phonetic_alphabet_nli
+- 143 bigbench/identify_odd_metaphor
+- 144 bigbench/mathematical_induction
+- 145 bigbench/odd_one_out
+- 146 bigbench/reasoning_about_colored_objects
+- 147 bigbench/strange_stories
+- 148 bigbench/evaluating_information_essentiality
+- 149 bigbench/figure_of_speech_detection
+- 150 bigbench/english_proverbs
+- 151 bigbench/general_knowledge
+- 152 bigbench/tracking_shuffled_objects
+- 153 bigbench/physics
+- 154 bigbench/anachronisms
+- 155 bigbench/simple_ethical_questions
+- 156 bigbench/logical_args
+- 157 bigbench/suicide_risk
+- 158 bigbench/sentence_ambiguity
+- 159 bigbench/temporal_sequences
+- 160 bigbench/penguins_in_a_table
+- 161 bigbench/sports_understanding
+- 162 bigbench/hyperbaton
+- 163 bigbench/code_line_description
+- 164 bigbench/question_selection
+- 165 bigbench/disambiguation_qa
+- 166 bigbench/date_understanding
+- 167 bigbench/play_dialog_same_or_different
+- 168 bigbench/salient_translation_error_detection
+- 169 bigbench/irony_identification
+- 170 bigbench/emojis_emotion_prediction
+- 171 bigbench/hindu_knowledge
+- 172 bigbench/conceptual_combinations
+- 173 bigbench/implicatures
+- 174 bigbench/movie_dialog_same_or_different
+- 175 bigbench/social_support
+- 176 bigbench/presuppositions_as_nli
+- 177 bigbench/vitaminc_fact_verification
+- 178 bigbench/hhh_alignment
+- 179 bigbench/implicit_relations
+- 180 bigbench/bbq_lite_json
+- 181 bigbench/phrase_relatedness
+- 182 bigbench/logical_deduction
+- 183 bigbench/discourse_marker_prediction
+- 184 bigbench/movie_recommendation
+- 185 bigbench/real_or_fake_text
+- 186 bigbench/formal_fallacies_syllogisms_negation
+- 187 bigbench/crass_ai
+- 188 blimp/inchoative
+- 189 blimp/principle_A_c_command
+- 190 blimp/matrix_question_npi_licensor_present
+- 191 blimp/wh_questions_subject_gap_long_distance
+- 192 blimp/sentential_subject_island
+- 193 blimp/existential_there_quantifiers_2
+- 194 blimp/sentential_negation_npi_scope
+- 195 blimp/complex_NP_island
+- 196 blimp/principle_A_reconstruction
+- 197 blimp/animate_subject_passive
+- 198 blimp/tough_vs_raising_1
+- 199 blimp/wh_vs_that_with_gap
+- 200 blimp/principle_A_domain_2
+- 201 blimp/npi_present_1
+- 202 blimp/wh_vs_that_with_gap_long_distance
+- 203 blimp/superlative_quantifiers_1
+- 204 blimp/npi_present_2
+- 205 blimp/wh_questions_object_gap
+- 206 blimp/coordinate_structure_constraint_complex_left_branch
+- 207 blimp/coordinate_structure_constraint_object_extraction
+- 208 blimp/left_branch_island_echo_question
+- 209 blimp/drop_argument
+- 210 cos_e/v1.0
+- 211 cosmos_qa
+- 212 dream
+- 213 openbookqa
+- 214 qasc
+- 215 quartz
+- 216 quail
+- 217 head_qa/en
+- 218 sciq
+- 219 social_i_qa
+- 220 wiki_hop
+- 221 wiqa
+- 222 piqa
+- 223 hellaswag
+- 224 super_glue/copa
+- 225 art
+- 226 hendrycks_test/moral_disputes
+- 227 hendrycks_test/moral_scenarios
+- 228 hendrycks_test/nutrition
+- 229 hendrycks_test/philosophy
+- 230 hendrycks_test/prehistory
+- 231 hendrycks_test/professional_accounting
+- 232 hendrycks_test/professional_law
+- 233 hendrycks_test/world_religions
+- 234 hendrycks_test/professional_psychology
+- 235 hendrycks_test/public_relations
+- 236 hendrycks_test/security_studies
+- 237 hendrycks_test/sociology
+- 238 hendrycks_test/us_foreign_policy
+- 239 hendrycks_test/virology
+- 240 hendrycks_test/miscellaneous
+- 241 hendrycks_test/professional_medicine
+- 242 hendrycks_test/medical_genetics
+- 243 hendrycks_test/college_mathematics
+- 244 hendrycks_test/management
+- 245 hendrycks_test/high_school_computer_science
+- 246 hendrycks_test/astronomy
+- 247 hendrycks_test/high_school_chemistry
+- 248 hendrycks_test/high_school_biology
+- 249 hendrycks_test/global_facts
+- 250 hendrycks_test/formal_logic
+- 251 hendrycks_test/elementary_mathematics
+- 252 hendrycks_test/high_school_european_history
+- 253 hendrycks_test/electrical_engineering
+- 254 hendrycks_test/conceptual_physics
+- 255 hendrycks_test/computer_security
+- 256 hendrycks_test/college_physics
+- 257 hendrycks_test/college_medicine
+- 258 hendrycks_test/college_computer_science
+- 259 hendrycks_test/college_chemistry
+- 260 hendrycks_test/college_biology
+- 261 hendrycks_test/econometrics
+- 262 hendrycks_test/clinical_knowledge
+- 263 hendrycks_test/anatomy
+- 264 hendrycks_test/marketing
+- 265 hendrycks_test/machine_learning
+- 266 hendrycks_test/logical_fallacies
+- 267 hendrycks_test/jurisprudence
+- 268 hendrycks_test/international_law
+- 269 hendrycks_test/human_sexuality
+- 270 hendrycks_test/human_aging
+- 271 hendrycks_test/high_school_world_history
+- 272 hendrycks_test/abstract_algebra
+- 273 hendrycks_test/high_school_us_history
+- 274 hendrycks_test/high_school_psychology
+- 275 hendrycks_test/high_school_physics
+- 276 hendrycks_test/high_school_microeconomics
+- 277 hendrycks_test/high_school_mathematics
+- 278 hendrycks_test/high_school_macroeconomics
+- 279 hendrycks_test/high_school_government_and_politics
+- 280 hendrycks_test/high_school_geography
+- 281 hendrycks_test/high_school_statistics
+- 282 hendrycks_test/business_ethics
+- 283 winogrande/winogrande_xl
+- 284 codah/codah
+- 285 ai2_arc/ARC-Challenge/challenge
+- 286 ai2_arc/ARC-Easy/challenge
+- 287 definite_pronoun_resolution
+- 288 swag
+- 289 math_qa
+- 290 utilitarianism
+- 291 TuringBench
+- 292 trec
+- 293 vitaminc/tals--vitaminc
+- 294 hope_edi/english
+- 295 rumoureval_2019/RumourEval2019
+- 296 ethos/binary
+- 297 ethos/multilabel
+- 298 glue/cola
+- 299 glue/sst2
+- 300 glue/mrpc
+- 301 glue/qqp
+- 302 glue/stsb
+- 303 glue/mnli
+- 304 glue/qnli
+- 305 glue/rte
+- 306 glue/wnli
+- 307 super_glue/boolq
+- 308 super_glue/cb
+- 309 super_glue/multirc
+- 310 super_glue/wic
+- 311 super_glue/axg
+- 312 tweet_eval/stance_feminist
+- 313 tweet_eval/stance_atheism
+- 314 tweet_eval/stance_hillary
+- 315 tweet_eval/stance_abortion
+- 316 tweet_eval/sentiment
+- 317 tweet_eval/offensive
+- 318 tweet_eval/stance_climate
+- 319 tweet_eval/irony
+- 320 tweet_eval/emotion
+- 321 tweet_eval/emoji
+- 322 tweet_eval/hate
+- 323 discovery/discovery
+- 324 pragmeval/switchboard
+- 325 pragmeval/squinky-informativeness
+- 326 pragmeval/emobank-arousal
+- 327 pragmeval/emobank-dominance
+- 328 pragmeval/emobank-valence
+- 329 pragmeval/mrda
+- 330 pragmeval/verifiability
+- 331 pragmeval/squinky-implicature
+- 332 pragmeval/squinky-formality
+- 333 pragmeval/gum
+- 334 pragmeval/emergent
+- 335 pragmeval/persuasiveness-premisetype
+- 336 pragmeval/pdtb
+- 337 pragmeval/persuasiveness-eloquence
+- 338 pragmeval/persuasiveness-specificity
+- 339 pragmeval/persuasiveness-strength
+- 340 pragmeval/sarcasm
+- 341 pragmeval/stac
+- 342 pragmeval/persuasiveness-claimtype
+- 343 pragmeval/persuasiveness-relevance
+- 344 lex_glue/eurlex
+- 345 lex_glue/scotus
+- 346 lex_glue/ledgar
+- 347 lex_glue/unfair_tos
+- 348 lex_glue/case_hold
+- 349 imdb
+- 350 rotten_tomatoes
+- 351 ag_news
+- 352 yelp_review_full/yelp_review_full
+- 353 financial_phrasebank/sentences_allagree
+- 354 poem_sentiment
+- 355 dbpedia_14/dbpedia_14
+- 356 amazon_polarity/amazon_polarity
+- 357 app_reviews
+- 358 hate_speech18
+- 359 sms_spam
+- 360 humicroedit/subtask-1
+- 361 humicroedit/subtask-2
+- 362 snips_built_in_intents
+- 363 banking77
+- 364 hate_speech_offensive
+- 365 hyperpartisan_news_detection/byarticle
+- 366 hyperpartisan_news_detection/bypublisher
+- 367 go_emotions/simplified
+- 368 scicite
+- 369 liar
+- 370 lexical_relation_classification/ROOT09
+- 371 lexical_relation_classification/EVALution
+- 372 lexical_relation_classification/CogALexV
+- 373 lexical_relation_classification/BLESS
+- 374 lexical_relation_classification/K&H+N
+- 375 linguisticprobing/coordination_inversion
+- 376 linguisticprobing/odd_man_out
+- 377 linguisticprobing/word_content
+- 378 linguisticprobing/obj_number
+- 379 linguisticprobing/past_present
+- 380 linguisticprobing/tree_depth
+- 381 linguisticprobing/sentence_length
+- 382 linguisticprobing/top_constituents
+- 383 linguisticprobing/bigram_shift
+- 384 linguisticprobing/subj_number
+- 385 crowdflower/sentiment_nuclear_power
+- 386 crowdflower/tweet_global_warming
+- 387 crowdflower/airline-sentiment
+- 388 crowdflower/economic-news
+- 389 crowdflower/political-media-audience
+- 390 crowdflower/political-media-bias
+- 391 crowdflower/political-media-message
+- 392 crowdflower/text_emotion
+- 393 crowdflower/corporate-messaging
+- 394 ethics/commonsense
+- 395 ethics/deontology
+- 396 ethics/justice
+- 397 ethics/virtue
+- 398 emo/emo2019
+- 399 google_wellformed_query
+- 400 tweets_hate_speech_detection
+- 401 adv_glue/adv_sst2
+- 402 adv_glue/adv_qqp
+- 403 adv_glue/adv_mnli
+- 404 adv_glue/adv_mnli_mismatched
+- 405 adv_glue/adv_qnli
+- 406 adv_glue/adv_rte
+- 407 has_part
+- 408 wnut_17/wnut_17
+- 409 ncbi_disease/ncbi_disease
+- 410 acronym_identification
+- 411 jnlpba/jnlpba
+- 412 species_800/species_800
+- 413 ontonotes_english/SpeedOfMagic--ontonotes_english
+- 414 blog_authorship_corpus/gender
+- 415 blog_authorship_corpus/age
+- 416 blog_authorship_corpus/horoscope
+- 417 blog_authorship_corpus/job
+- 418 open_question_type
+- 419 health_fact
+- 420 commonsense_qa
+- 421 mc_taco
+- 422 ade_corpus_v2/Ade_corpus_v2_classification
+- 423 discosense
+- 424 circa
+- 425 code_x_glue_cc_defect_detection
+- 426 code_x_glue_cc_clone_detection_big_clone_bench
+- 427 code_x_glue_cc_code_refinement/medium
+- 428 EffectiveFeedbackStudentWriting
+- 429 promptSentiment
+- 430 promptNLI
+- 431 promptSpoke
+- 432 promptProficiency
+- 433 promptGrammar
+- 434 promptCoherence
+- 435 phrase_similarity
+- 436 scientific-exaggeration-detection
+- 437 quarel
+- 438 fever-evidence-related/mwong--fever-related
+- 439 numer_sense
+- 440 dynasent/dynabench.dynasent.r1.all/r1
+- 441 dynasent/dynabench.dynasent.r2.all/r2
+- 442 Sarcasm_News_Headline
+- 443 sem_eval_2010_task_8

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "microsoft/deberta-v3-base",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}