AswanthCManoj
commited on
Commit
•
6e774e2
1
Parent(s):
b560386
Updated model
Browse files- README.md +379 -0
- added_tokens.json +3 -0
- config.json +1039 -0
- gitattributes.txt +34 -0
- model.safetensors +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- spm.model +3 -0
- tasks.md +444 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
README.md
CHANGED
@@ -1,3 +1,382 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
language: en
|
4 |
+
tags:
|
5 |
+
- deberta-v3-base
|
6 |
+
- deberta-v3
|
7 |
+
- deberta
|
8 |
+
- text-classification
|
9 |
+
- nli
|
10 |
+
- natural-language-inference
|
11 |
+
- multitask
|
12 |
+
- multi-task
|
13 |
+
- pipeline
|
14 |
+
- extreme-multi-task
|
15 |
+
- extreme-mtl
|
16 |
+
- tasksource
|
17 |
+
- zero-shot
|
18 |
+
- rlhf
|
19 |
+
model-index:
|
20 |
+
- name: deberta-v3-base-tasksource-nli
|
21 |
+
results:
|
22 |
+
- task:
|
23 |
+
type: text-classification
|
24 |
+
name: Text Classification
|
25 |
+
dataset:
|
26 |
+
name: glue
|
27 |
+
type: glue
|
28 |
+
config: rte
|
29 |
+
split: validation
|
30 |
+
metrics:
|
31 |
+
- type: accuracy
|
32 |
+
value: 0.89
|
33 |
+
- task:
|
34 |
+
type: natural-language-inference
|
35 |
+
name: Natural Language Inference
|
36 |
+
dataset:
|
37 |
+
name: anli-r3
|
38 |
+
type: anli
|
39 |
+
config: plain_text
|
40 |
+
split: validation
|
41 |
+
metrics:
|
42 |
+
- type: accuracy
|
43 |
+
value: 0.52
|
44 |
+
name: Accuracy
|
45 |
+
datasets:
|
46 |
+
- glue
|
47 |
+
- super_glue
|
48 |
+
- anli
|
49 |
+
- tasksource/babi_nli
|
50 |
+
- sick
|
51 |
+
- snli
|
52 |
+
- scitail
|
53 |
+
- OpenAssistant/oasst1
|
54 |
+
- universal_dependencies
|
55 |
+
- hans
|
56 |
+
- qbao775/PARARULE-Plus
|
57 |
+
- alisawuffles/WANLI
|
58 |
+
- metaeval/recast
|
59 |
+
- sileod/probability_words_nli
|
60 |
+
- joey234/nan-nli
|
61 |
+
- pietrolesci/nli_fever
|
62 |
+
- pietrolesci/breaking_nli
|
63 |
+
- pietrolesci/conj_nli
|
64 |
+
- pietrolesci/fracas
|
65 |
+
- pietrolesci/dialogue_nli
|
66 |
+
- pietrolesci/mpe
|
67 |
+
- pietrolesci/dnc
|
68 |
+
- pietrolesci/gpt3_nli
|
69 |
+
- pietrolesci/recast_white
|
70 |
+
- pietrolesci/joci
|
71 |
+
- martn-nguyen/contrast_nli
|
72 |
+
- pietrolesci/robust_nli
|
73 |
+
- pietrolesci/robust_nli_is_sd
|
74 |
+
- pietrolesci/robust_nli_li_ts
|
75 |
+
- pietrolesci/gen_debiased_nli
|
76 |
+
- pietrolesci/add_one_rte
|
77 |
+
- metaeval/imppres
|
78 |
+
- pietrolesci/glue_diagnostics
|
79 |
+
- hlgd
|
80 |
+
- PolyAI/banking77
|
81 |
+
- paws
|
82 |
+
- quora
|
83 |
+
- medical_questions_pairs
|
84 |
+
- conll2003
|
85 |
+
- nlpaueb/finer-139
|
86 |
+
- Anthropic/hh-rlhf
|
87 |
+
- Anthropic/model-written-evals
|
88 |
+
- truthful_qa
|
89 |
+
- nightingal3/fig-qa
|
90 |
+
- tasksource/bigbench
|
91 |
+
- blimp
|
92 |
+
- cos_e
|
93 |
+
- cosmos_qa
|
94 |
+
- dream
|
95 |
+
- openbookqa
|
96 |
+
- qasc
|
97 |
+
- quartz
|
98 |
+
- quail
|
99 |
+
- head_qa
|
100 |
+
- sciq
|
101 |
+
- social_i_qa
|
102 |
+
- wiki_hop
|
103 |
+
- wiqa
|
104 |
+
- piqa
|
105 |
+
- hellaswag
|
106 |
+
- pkavumba/balanced-copa
|
107 |
+
- 12ml/e-CARE
|
108 |
+
- art
|
109 |
+
- tasksource/mmlu
|
110 |
+
- winogrande
|
111 |
+
- codah
|
112 |
+
- ai2_arc
|
113 |
+
- definite_pronoun_resolution
|
114 |
+
- swag
|
115 |
+
- math_qa
|
116 |
+
- metaeval/utilitarianism
|
117 |
+
- mteb/amazon_counterfactual
|
118 |
+
- SetFit/insincere-questions
|
119 |
+
- SetFit/toxic_conversations
|
120 |
+
- turingbench/TuringBench
|
121 |
+
- trec
|
122 |
+
- tals/vitaminc
|
123 |
+
- hope_edi
|
124 |
+
- strombergnlp/rumoureval_2019
|
125 |
+
- ethos
|
126 |
+
- tweet_eval
|
127 |
+
- discovery
|
128 |
+
- pragmeval
|
129 |
+
- silicone
|
130 |
+
- lex_glue
|
131 |
+
- papluca/language-identification
|
132 |
+
- imdb
|
133 |
+
- rotten_tomatoes
|
134 |
+
- ag_news
|
135 |
+
- yelp_review_full
|
136 |
+
- financial_phrasebank
|
137 |
+
- poem_sentiment
|
138 |
+
- dbpedia_14
|
139 |
+
- amazon_polarity
|
140 |
+
- app_reviews
|
141 |
+
- hate_speech18
|
142 |
+
- sms_spam
|
143 |
+
- humicroedit
|
144 |
+
- snips_built_in_intents
|
145 |
+
- banking77
|
146 |
+
- hate_speech_offensive
|
147 |
+
- yahoo_answers_topics
|
148 |
+
- pacovaldez/stackoverflow-questions
|
149 |
+
- zapsdcn/hyperpartisan_news
|
150 |
+
- zapsdcn/sciie
|
151 |
+
- zapsdcn/citation_intent
|
152 |
+
- go_emotions
|
153 |
+
- allenai/scicite
|
154 |
+
- liar
|
155 |
+
- relbert/lexical_relation_classification
|
156 |
+
- metaeval/linguisticprobing
|
157 |
+
- tasksource/crowdflower
|
158 |
+
- metaeval/ethics
|
159 |
+
- emo
|
160 |
+
- google_wellformed_query
|
161 |
+
- tweets_hate_speech_detection
|
162 |
+
- has_part
|
163 |
+
- wnut_17
|
164 |
+
- ncbi_disease
|
165 |
+
- acronym_identification
|
166 |
+
- jnlpba
|
167 |
+
- species_800
|
168 |
+
- SpeedOfMagic/ontonotes_english
|
169 |
+
- blog_authorship_corpus
|
170 |
+
- launch/open_question_type
|
171 |
+
- health_fact
|
172 |
+
- commonsense_qa
|
173 |
+
- mc_taco
|
174 |
+
- ade_corpus_v2
|
175 |
+
- prajjwal1/discosense
|
176 |
+
- circa
|
177 |
+
- PiC/phrase_similarity
|
178 |
+
- copenlu/scientific-exaggeration-detection
|
179 |
+
- quarel
|
180 |
+
- mwong/fever-evidence-related
|
181 |
+
- numer_sense
|
182 |
+
- dynabench/dynasent
|
183 |
+
- raquiba/Sarcasm_News_Headline
|
184 |
+
- sem_eval_2010_task_8
|
185 |
+
- demo-org/auditor_review
|
186 |
+
- medmcqa
|
187 |
+
- aqua_rat
|
188 |
+
- RuyuanWan/Dynasent_Disagreement
|
189 |
+
- RuyuanWan/Politeness_Disagreement
|
190 |
+
- RuyuanWan/SBIC_Disagreement
|
191 |
+
- RuyuanWan/SChem_Disagreement
|
192 |
+
- RuyuanWan/Dilemmas_Disagreement
|
193 |
+
- lucasmccabe/logiqa
|
194 |
+
- wiki_qa
|
195 |
+
- metaeval/cycic_classification
|
196 |
+
- metaeval/cycic_multiplechoice
|
197 |
+
- metaeval/sts-companion
|
198 |
+
- metaeval/commonsense_qa_2.0
|
199 |
+
- metaeval/lingnli
|
200 |
+
- metaeval/monotonicity-entailment
|
201 |
+
- metaeval/arct
|
202 |
+
- metaeval/scinli
|
203 |
+
- metaeval/naturallogic
|
204 |
+
- onestop_qa
|
205 |
+
- demelin/moral_stories
|
206 |
+
- corypaik/prost
|
207 |
+
- aps/dynahate
|
208 |
+
- metaeval/syntactic-augmentation-nli
|
209 |
+
- metaeval/autotnli
|
210 |
+
- lasha-nlp/CONDAQA
|
211 |
+
- openai/webgpt_comparisons
|
212 |
+
- Dahoas/synthetic-instruct-gptj-pairwise
|
213 |
+
- metaeval/scruples
|
214 |
+
- metaeval/wouldyourather
|
215 |
+
- sileod/attempto-nli
|
216 |
+
- metaeval/defeasible-nli
|
217 |
+
- metaeval/help-nli
|
218 |
+
- metaeval/nli-veridicality-transitivity
|
219 |
+
- metaeval/natural-language-satisfiability
|
220 |
+
- metaeval/lonli
|
221 |
+
- tasksource/dadc-limit-nli
|
222 |
+
- ColumbiaNLP/FLUTE
|
223 |
+
- metaeval/strategy-qa
|
224 |
+
- openai/summarize_from_feedback
|
225 |
+
- tasksource/folio
|
226 |
+
- metaeval/tomi-nli
|
227 |
+
- metaeval/avicenna
|
228 |
+
- stanfordnlp/SHP
|
229 |
+
- GBaker/MedQA-USMLE-4-options-hf
|
230 |
+
- GBaker/MedQA-USMLE-4-options
|
231 |
+
- sileod/wikimedqa
|
232 |
+
- declare-lab/cicero
|
233 |
+
- amydeng2000/CREAK
|
234 |
+
- metaeval/mutual
|
235 |
+
- inverse-scaling/NeQA
|
236 |
+
- inverse-scaling/quote-repetition
|
237 |
+
- inverse-scaling/redefine-math
|
238 |
+
- tasksource/puzzte
|
239 |
+
- metaeval/implicatures
|
240 |
+
- race
|
241 |
+
- metaeval/spartqa-yn
|
242 |
+
- metaeval/spartqa-mchoice
|
243 |
+
- metaeval/temporal-nli
|
244 |
+
- metaeval/ScienceQA_text_only
|
245 |
+
- AndyChiang/cloth
|
246 |
+
- metaeval/logiqa-2.0-nli
|
247 |
+
- tasksource/oasst1_dense_flat
|
248 |
+
- metaeval/boolq-natural-perturbations
|
249 |
+
- metaeval/path-naturalness-prediction
|
250 |
+
- riddle_sense
|
251 |
+
- Jiangjie/ekar_english
|
252 |
+
- metaeval/implicit-hate-stg1
|
253 |
+
- metaeval/chaos-mnli-ambiguity
|
254 |
+
- IlyaGusev/headline_cause
|
255 |
+
- metaeval/race-c
|
256 |
+
- metaeval/equate
|
257 |
+
- metaeval/ambient
|
258 |
+
- AndyChiang/dgen
|
259 |
+
- metaeval/clcd-english
|
260 |
+
- civil_comments
|
261 |
+
- metaeval/acceptability-prediction
|
262 |
+
- maximedb/twentyquestions
|
263 |
+
- metaeval/counterfactually-augmented-snli
|
264 |
+
- tasksource/I2D2
|
265 |
+
- sileod/mindgames
|
266 |
+
- metaeval/counterfactually-augmented-imdb
|
267 |
+
- metaeval/cnli
|
268 |
+
- metaeval/reclor
|
269 |
+
- tasksource/oasst1_pairwise_rlhf_reward
|
270 |
+
- tasksource/zero-shot-label-nli
|
271 |
+
- webis/args_me
|
272 |
+
- webis/Touche23-ValueEval
|
273 |
+
- tasksource/starcon
|
274 |
+
- tasksource/ruletaker
|
275 |
+
- lighteval/lsat_qa
|
276 |
+
- tasksource/ConTRoL-nli
|
277 |
+
- tasksource/tracie
|
278 |
+
- tasksource/sherliic
|
279 |
+
- tasksource/sen-making
|
280 |
+
- tasksource/winowhy
|
281 |
+
- mediabiasgroup/mbib-base
|
282 |
+
- tasksource/robustLR
|
283 |
+
- CLUTRR/v1
|
284 |
+
- tasksource/logical-fallacy
|
285 |
+
- tasksource/parade
|
286 |
+
- tasksource/cladder
|
287 |
+
- tasksource/subjectivity
|
288 |
+
- tasksource/MOH
|
289 |
+
- tasksource/VUAC
|
290 |
+
- tasksource/TroFi
|
291 |
+
- sharc_modified
|
292 |
+
- tasksource/conceptrules_v2
|
293 |
+
- tasksource/disrpt
|
294 |
+
- conll2000
|
295 |
+
- DFKI-SLT/few-nerd
|
296 |
+
- tasksource/com2sense
|
297 |
+
- tasksource/scone
|
298 |
+
- tasksource/winodict
|
299 |
+
- tasksource/fool-me-twice
|
300 |
+
- tasksource/monli
|
301 |
+
- tasksource/corr2cause
|
302 |
+
- tasksource/apt
|
303 |
+
- zeroshot/twitter-financial-news-sentiment
|
304 |
+
- tasksource/icl-symbol-tuning-instruct
|
305 |
+
- tasksource/SpaceNLI
|
306 |
+
- sihaochen/propsegment
|
307 |
+
- HannahRoseKirk/HatemojiBuild
|
308 |
+
- tasksource/regset
|
309 |
+
- tasksource/babi_nli
|
310 |
+
- lmsys/chatbot_arena_conversations
|
311 |
+
metrics:
|
312 |
+
- accuracy
|
313 |
+
library_name: transformers
|
314 |
+
pipeline_tag: zero-shot-classification
|
315 |
---
|
316 |
+
|
317 |
+
# Model Card for DeBERTa-v3-base-tasksource-nli
|
318 |
+
|
319 |
+
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/).
|
320 |
+
This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for:
|
321 |
+
- Zero-shot entailment-based classification pipeline (similar to bart-mnli), see [ZS].
|
322 |
+
- Natural language inference, and many other tasks with tasksource-adapters, see [TA]
|
323 |
+
- Further fine-tuning with a new task (classification, token classification or multiple-choice).
|
324 |
+
|
325 |
+
# [ZS] Zero-shot classification pipeline
|
326 |
+
```python
|
327 |
+
from transformers import pipeline
|
328 |
+
classifier = pipeline("zero-shot-classification",model="sileod/deberta-v3-base-tasksource-nli")
|
329 |
+
|
330 |
+
text = "one day I will see the world"
|
331 |
+
candidate_labels = ['travel', 'cooking', 'dancing']
|
332 |
+
classifier(text, candidate_labels)
|
333 |
+
```
|
334 |
+
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.
|
335 |
+
|
336 |
+
# [TA] Tasksource-adapters: 1 line access to hundreds of tasks
|
337 |
+
|
338 |
+
```python
|
339 |
+
!pip install tasknet tasksource
|
340 |
+
import tasknet as tn
|
341 |
+
pipe = tn.load_pipeline('sileod/deberta-v3-base-tasksource-nli','glue/sst2') # works for 500+ tasksource tasks
|
342 |
+
pipe(['That movie was great !', 'Awful movie.'])
|
343 |
+
# [{'label': 'positive', 'score': 0.9956}, {'label': 'negative', 'score': 0.9967}]
|
344 |
+
```
|
345 |
+
The list of tasks is available in model config.json.
|
346 |
+
This is more efficient than ZS since it requires only one forward pass per example, but it is less flexible.
|
347 |
+
|
348 |
+
|
349 |
+
## Evaluation
|
350 |
+
This model ranked 1st among all models with the microsoft/deberta-v3-base architecture according to the IBM model recycling evaluation.
|
351 |
+
https://ibm.github.io/model-recycling/
|
352 |
+
|
353 |
+
### Software and training details
|
354 |
+
|
355 |
+
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.
|
356 |
+
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.
|
357 |
+
|
358 |
+
|
359 |
+
https://github.com/sileod/tasksource/ \
|
360 |
+
https://github.com/sileod/tasknet/ \
|
361 |
+
Training code: https://colab.research.google.com/drive/1iB4Oxl9_B5W3ZDzXoWJN-olUbqLBxgQS?usp=sharing
|
362 |
+
|
363 |
+
# Citation
|
364 |
+
|
365 |
+
More details on this [article:](https://arxiv.org/abs/2301.05948)
|
366 |
+
```
|
367 |
+
@article{sileo2023tasksource,
|
368 |
+
title={tasksource: Structured Dataset Preprocessing Annotations for Frictionless Extreme Multi-Task Learning and Evaluation},
|
369 |
+
author={Sileo, Damien},
|
370 |
+
url= {https://arxiv.org/abs/2301.05948},
|
371 |
+
journal={arXiv preprint arXiv:2301.05948},
|
372 |
+
year={2023}
|
373 |
+
}
|
374 |
+
```
|
375 |
+
|
376 |
+
|
377 |
+
# Model Card Contact
|
378 |
+
|
379 |
+
damien.sileo@inria.fr
|
380 |
+
|
381 |
+
|
382 |
+
</details>
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
config.json
ADDED
@@ -0,0 +1,1039 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifiers_size": [
|
8 |
+
3,
|
9 |
+
2,
|
10 |
+
2,
|
11 |
+
2,
|
12 |
+
2,
|
13 |
+
2,
|
14 |
+
1,
|
15 |
+
2,
|
16 |
+
3,
|
17 |
+
2,
|
18 |
+
2,
|
19 |
+
2,
|
20 |
+
3,
|
21 |
+
3,
|
22 |
+
3,
|
23 |
+
3,
|
24 |
+
1,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
2,
|
28 |
+
2,
|
29 |
+
3,
|
30 |
+
2,
|
31 |
+
6,
|
32 |
+
2,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2,
|
39 |
+
2,
|
40 |
+
2,
|
41 |
+
3,
|
42 |
+
3,
|
43 |
+
3,
|
44 |
+
3,
|
45 |
+
3,
|
46 |
+
3,
|
47 |
+
3,
|
48 |
+
2,
|
49 |
+
2,
|
50 |
+
2,
|
51 |
+
2,
|
52 |
+
5,
|
53 |
+
3,
|
54 |
+
3,
|
55 |
+
3,
|
56 |
+
3,
|
57 |
+
3,
|
58 |
+
3,
|
59 |
+
3,
|
60 |
+
3,
|
61 |
+
2,
|
62 |
+
2,
|
63 |
+
2,
|
64 |
+
3,
|
65 |
+
3,
|
66 |
+
3,
|
67 |
+
3,
|
68 |
+
3,
|
69 |
+
3,
|
70 |
+
3,
|
71 |
+
3,
|
72 |
+
2,
|
73 |
+
2,
|
74 |
+
2,
|
75 |
+
2,
|
76 |
+
47,
|
77 |
+
23,
|
78 |
+
9,
|
79 |
+
1,
|
80 |
+
1,
|
81 |
+
1,
|
82 |
+
1,
|
83 |
+
1,
|
84 |
+
1,
|
85 |
+
1,
|
86 |
+
1,
|
87 |
+
1,
|
88 |
+
1,
|
89 |
+
1,
|
90 |
+
1,
|
91 |
+
1,
|
92 |
+
1,
|
93 |
+
1,
|
94 |
+
1,
|
95 |
+
1,
|
96 |
+
1,
|
97 |
+
1,
|
98 |
+
1,
|
99 |
+
1,
|
100 |
+
1,
|
101 |
+
1,
|
102 |
+
1,
|
103 |
+
1,
|
104 |
+
1,
|
105 |
+
1,
|
106 |
+
1,
|
107 |
+
1,
|
108 |
+
1,
|
109 |
+
1,
|
110 |
+
1,
|
111 |
+
1,
|
112 |
+
1,
|
113 |
+
1,
|
114 |
+
1,
|
115 |
+
1,
|
116 |
+
1,
|
117 |
+
1,
|
118 |
+
1,
|
119 |
+
1,
|
120 |
+
1,
|
121 |
+
1,
|
122 |
+
1,
|
123 |
+
1,
|
124 |
+
1,
|
125 |
+
1,
|
126 |
+
1,
|
127 |
+
1,
|
128 |
+
1,
|
129 |
+
1,
|
130 |
+
1,
|
131 |
+
1,
|
132 |
+
1,
|
133 |
+
1,
|
134 |
+
1,
|
135 |
+
1,
|
136 |
+
1,
|
137 |
+
1,
|
138 |
+
1,
|
139 |
+
1,
|
140 |
+
1,
|
141 |
+
1,
|
142 |
+
1,
|
143 |
+
1,
|
144 |
+
1,
|
145 |
+
1,
|
146 |
+
1,
|
147 |
+
1,
|
148 |
+
1,
|
149 |
+
1,
|
150 |
+
1,
|
151 |
+
1,
|
152 |
+
1,
|
153 |
+
1,
|
154 |
+
1,
|
155 |
+
1,
|
156 |
+
1,
|
157 |
+
1,
|
158 |
+
1,
|
159 |
+
1,
|
160 |
+
1,
|
161 |
+
1,
|
162 |
+
1,
|
163 |
+
1,
|
164 |
+
1,
|
165 |
+
1,
|
166 |
+
1,
|
167 |
+
1,
|
168 |
+
1,
|
169 |
+
1,
|
170 |
+
1,
|
171 |
+
1,
|
172 |
+
1,
|
173 |
+
1,
|
174 |
+
1,
|
175 |
+
1,
|
176 |
+
1,
|
177 |
+
1,
|
178 |
+
1,
|
179 |
+
1,
|
180 |
+
1,
|
181 |
+
1,
|
182 |
+
1,
|
183 |
+
1,
|
184 |
+
1,
|
185 |
+
1,
|
186 |
+
1,
|
187 |
+
1,
|
188 |
+
1,
|
189 |
+
1,
|
190 |
+
1,
|
191 |
+
1,
|
192 |
+
1,
|
193 |
+
1,
|
194 |
+
1,
|
195 |
+
1,
|
196 |
+
1,
|
197 |
+
1,
|
198 |
+
1,
|
199 |
+
1,
|
200 |
+
1,
|
201 |
+
1,
|
202 |
+
1,
|
203 |
+
1,
|
204 |
+
1,
|
205 |
+
1,
|
206 |
+
1,
|
207 |
+
1,
|
208 |
+
2,
|
209 |
+
2,
|
210 |
+
2,
|
211 |
+
2,
|
212 |
+
2,
|
213 |
+
2,
|
214 |
+
20,
|
215 |
+
50,
|
216 |
+
3,
|
217 |
+
3,
|
218 |
+
4,
|
219 |
+
2,
|
220 |
+
8,
|
221 |
+
3,
|
222 |
+
3,
|
223 |
+
3,
|
224 |
+
3,
|
225 |
+
20,
|
226 |
+
3,
|
227 |
+
2,
|
228 |
+
2,
|
229 |
+
2,
|
230 |
+
4,
|
231 |
+
3,
|
232 |
+
174,
|
233 |
+
2,
|
234 |
+
2,
|
235 |
+
2,
|
236 |
+
2,
|
237 |
+
2,
|
238 |
+
41,
|
239 |
+
51,
|
240 |
+
3,
|
241 |
+
2,
|
242 |
+
3,
|
243 |
+
17,
|
244 |
+
18,
|
245 |
+
2,
|
246 |
+
8,
|
247 |
+
2,
|
248 |
+
2,
|
249 |
+
2,
|
250 |
+
2,
|
251 |
+
3,
|
252 |
+
16,
|
253 |
+
11,
|
254 |
+
3,
|
255 |
+
42,
|
256 |
+
3,
|
257 |
+
7,
|
258 |
+
12,
|
259 |
+
7,
|
260 |
+
4,
|
261 |
+
100,
|
262 |
+
13,
|
263 |
+
100,
|
264 |
+
8,
|
265 |
+
1,
|
266 |
+
20,
|
267 |
+
2,
|
268 |
+
2,
|
269 |
+
4,
|
270 |
+
5,
|
271 |
+
3,
|
272 |
+
4,
|
273 |
+
14,
|
274 |
+
2,
|
275 |
+
6,
|
276 |
+
4,
|
277 |
+
2,
|
278 |
+
1,
|
279 |
+
3,
|
280 |
+
10,
|
281 |
+
3,
|
282 |
+
10,
|
283 |
+
4,
|
284 |
+
2,
|
285 |
+
7,
|
286 |
+
6,
|
287 |
+
28,
|
288 |
+
3,
|
289 |
+
6,
|
290 |
+
4,
|
291 |
+
5,
|
292 |
+
6,
|
293 |
+
3,
|
294 |
+
7,
|
295 |
+
2,
|
296 |
+
20,
|
297 |
+
2,
|
298 |
+
2,
|
299 |
+
7,
|
300 |
+
2,
|
301 |
+
6,
|
302 |
+
2,
|
303 |
+
2,
|
304 |
+
2,
|
305 |
+
13,
|
306 |
+
3,
|
307 |
+
4,
|
308 |
+
3,
|
309 |
+
2,
|
310 |
+
4,
|
311 |
+
2,
|
312 |
+
9,
|
313 |
+
2,
|
314 |
+
2,
|
315 |
+
2,
|
316 |
+
2,
|
317 |
+
4,
|
318 |
+
1,
|
319 |
+
2,
|
320 |
+
1,
|
321 |
+
13,
|
322 |
+
3,
|
323 |
+
5,
|
324 |
+
11,
|
325 |
+
37,
|
326 |
+
2,
|
327 |
+
49,
|
328 |
+
12,
|
329 |
+
40,
|
330 |
+
10,
|
331 |
+
4,
|
332 |
+
1,
|
333 |
+
2,
|
334 |
+
2,
|
335 |
+
1,
|
336 |
+
5,
|
337 |
+
2,
|
338 |
+
3,
|
339 |
+
2,
|
340 |
+
2,
|
341 |
+
12,
|
342 |
+
3,
|
343 |
+
3,
|
344 |
+
2,
|
345 |
+
19,
|
346 |
+
3,
|
347 |
+
1,
|
348 |
+
2,
|
349 |
+
2,
|
350 |
+
2,
|
351 |
+
2,
|
352 |
+
2,
|
353 |
+
1,
|
354 |
+
2,
|
355 |
+
2,
|
356 |
+
1,
|
357 |
+
1,
|
358 |
+
2,
|
359 |
+
3,
|
360 |
+
2,
|
361 |
+
1,
|
362 |
+
4,
|
363 |
+
4,
|
364 |
+
1,
|
365 |
+
1,
|
366 |
+
1,
|
367 |
+
2,
|
368 |
+
3,
|
369 |
+
2,
|
370 |
+
3,
|
371 |
+
1,
|
372 |
+
1,
|
373 |
+
2,
|
374 |
+
1,
|
375 |
+
3,
|
376 |
+
2,
|
377 |
+
2,
|
378 |
+
2,
|
379 |
+
2,
|
380 |
+
2,
|
381 |
+
3,
|
382 |
+
2,
|
383 |
+
2,
|
384 |
+
2,
|
385 |
+
1,
|
386 |
+
3,
|
387 |
+
2,
|
388 |
+
2,
|
389 |
+
1,
|
390 |
+
1,
|
391 |
+
1,
|
392 |
+
1,
|
393 |
+
2,
|
394 |
+
1,
|
395 |
+
1,
|
396 |
+
1,
|
397 |
+
1,
|
398 |
+
4,
|
399 |
+
1,
|
400 |
+
1,
|
401 |
+
1,
|
402 |
+
1,
|
403 |
+
3,
|
404 |
+
1,
|
405 |
+
3,
|
406 |
+
1,
|
407 |
+
2,
|
408 |
+
2,
|
409 |
+
1,
|
410 |
+
2,
|
411 |
+
3,
|
412 |
+
3,
|
413 |
+
2,
|
414 |
+
1,
|
415 |
+
3,
|
416 |
+
1,
|
417 |
+
1,
|
418 |
+
3,
|
419 |
+
1,
|
420 |
+
3,
|
421 |
+
2,
|
422 |
+
1,
|
423 |
+
1,
|
424 |
+
1,
|
425 |
+
2,
|
426 |
+
2,
|
427 |
+
50,
|
428 |
+
50,
|
429 |
+
50,
|
430 |
+
50,
|
431 |
+
2,
|
432 |
+
1,
|
433 |
+
1,
|
434 |
+
1,
|
435 |
+
1,
|
436 |
+
1,
|
437 |
+
1,
|
438 |
+
1,
|
439 |
+
1,
|
440 |
+
1,
|
441 |
+
1,
|
442 |
+
1,
|
443 |
+
2,
|
444 |
+
2,
|
445 |
+
2,
|
446 |
+
2,
|
447 |
+
77,
|
448 |
+
2,
|
449 |
+
1,
|
450 |
+
3,
|
451 |
+
2,
|
452 |
+
2,
|
453 |
+
1,
|
454 |
+
1,
|
455 |
+
2,
|
456 |
+
2,
|
457 |
+
2,
|
458 |
+
2,
|
459 |
+
2,
|
460 |
+
2,
|
461 |
+
2,
|
462 |
+
2,
|
463 |
+
2,
|
464 |
+
3,
|
465 |
+
18,
|
466 |
+
13,
|
467 |
+
2,
|
468 |
+
2,
|
469 |
+
2,
|
470 |
+
2,
|
471 |
+
2,
|
472 |
+
2,
|
473 |
+
4,
|
474 |
+
2,
|
475 |
+
24,
|
476 |
+
23,
|
477 |
+
67,
|
478 |
+
279,
|
479 |
+
3,
|
480 |
+
2,
|
481 |
+
2,
|
482 |
+
1,
|
483 |
+
2,
|
484 |
+
2,
|
485 |
+
3,
|
486 |
+
1,
|
487 |
+
2,
|
488 |
+
3,
|
489 |
+
2,
|
490 |
+
3,
|
491 |
+
3,
|
492 |
+
2,
|
493 |
+
2,
|
494 |
+
4,
|
495 |
+
1,
|
496 |
+
17,
|
497 |
+
2,
|
498 |
+
3,
|
499 |
+
3,
|
500 |
+
3,
|
501 |
+
1,
|
502 |
+
1
|
503 |
+
],
|
504 |
+
"hidden_act": "gelu",
|
505 |
+
"hidden_dropout_prob": 0.1,
|
506 |
+
"hidden_size": 768,
|
507 |
+
"id2label": {
|
508 |
+
"0": "entailment",
|
509 |
+
"1": "neutral",
|
510 |
+
"2": "contradiction"
|
511 |
+
},
|
512 |
+
"initializer_range": 0.02,
|
513 |
+
"intermediate_size": 3072,
|
514 |
+
"label2id": {
|
515 |
+
"contradiction": 2,
|
516 |
+
"entailment": 0,
|
517 |
+
"neutral": 1
|
518 |
+
},
|
519 |
+
"layer_norm_eps": 1e-07,
|
520 |
+
"max_position_embeddings": 512,
|
521 |
+
"max_relative_positions": -1,
|
522 |
+
"model_type": "deberta-v2",
|
523 |
+
"norm_rel_ebd": "layer_norm",
|
524 |
+
"num_attention_heads": 12,
|
525 |
+
"num_hidden_layers": 12,
|
526 |
+
"pad_token_id": 0,
|
527 |
+
"pooler_dropout": 0,
|
528 |
+
"pooler_hidden_act": "gelu",
|
529 |
+
"pooler_hidden_size": 768,
|
530 |
+
"pos_att_type": [
|
531 |
+
"p2c",
|
532 |
+
"c2p"
|
533 |
+
],
|
534 |
+
"position_biased_input": false,
|
535 |
+
"position_buckets": 256,
|
536 |
+
"relative_attention": true,
|
537 |
+
"share_att_key": true,
|
538 |
+
"tasks": [
|
539 |
+
"glue/mnli",
|
540 |
+
"glue/qnli",
|
541 |
+
"glue/rte",
|
542 |
+
"glue/wnli",
|
543 |
+
"glue/mrpc",
|
544 |
+
"glue/qqp",
|
545 |
+
"glue/stsb",
|
546 |
+
"super_glue/boolq",
|
547 |
+
"super_glue/cb",
|
548 |
+
"super_glue/multirc",
|
549 |
+
"super_glue/wic",
|
550 |
+
"super_glue/axg",
|
551 |
+
"anli/a1",
|
552 |
+
"anli/a2",
|
553 |
+
"anli/a3",
|
554 |
+
"sick/label",
|
555 |
+
"sick/relatedness",
|
556 |
+
"sick/entailment_AB",
|
557 |
+
"snli",
|
558 |
+
"scitail/snli_format",
|
559 |
+
"hans",
|
560 |
+
"WANLI",
|
561 |
+
"recast/recast_factuality",
|
562 |
+
"recast/recast_kg_relations",
|
563 |
+
"recast/recast_puns",
|
564 |
+
"recast/recast_sentiment",
|
565 |
+
"recast/recast_verbnet",
|
566 |
+
"recast/recast_ner",
|
567 |
+
"recast/recast_verbcorner",
|
568 |
+
"recast/recast_megaveridicality",
|
569 |
+
"probability_words_nli/reasoning_2hop",
|
570 |
+
"probability_words_nli/usnli",
|
571 |
+
"probability_words_nli/reasoning_1hop",
|
572 |
+
"nan-nli/joey234--nan-nli",
|
573 |
+
"nli_fever",
|
574 |
+
"breaking_nli",
|
575 |
+
"conj_nli",
|
576 |
+
"fracas",
|
577 |
+
"dialogue_nli",
|
578 |
+
"mpe",
|
579 |
+
"dnc",
|
580 |
+
"recast_white/fnplus",
|
581 |
+
"recast_white/sprl",
|
582 |
+
"recast_white/dpr",
|
583 |
+
"joci",
|
584 |
+
"robust_nli/IS_CS",
|
585 |
+
"robust_nli/LI_LI",
|
586 |
+
"robust_nli/ST_WO",
|
587 |
+
"robust_nli/PI_SP",
|
588 |
+
"robust_nli/PI_CD",
|
589 |
+
"robust_nli/ST_SE",
|
590 |
+
"robust_nli/ST_NE",
|
591 |
+
"robust_nli/ST_LM",
|
592 |
+
"robust_nli_is_sd",
|
593 |
+
"robust_nli_li_ts",
|
594 |
+
"add_one_rte",
|
595 |
+
"imppres/implicature_numerals_2_3/log",
|
596 |
+
"imppres/implicature_modals/log",
|
597 |
+
"imppres/implicature_gradable_verb/log",
|
598 |
+
"imppres/implicature_gradable_adjective/log",
|
599 |
+
"imppres/implicature_connectives/log",
|
600 |
+
"imppres/implicature_numerals_10_100/log",
|
601 |
+
"imppres/implicature_quantifiers/log",
|
602 |
+
"glue_diagnostics/diagnostics",
|
603 |
+
"hlgd",
|
604 |
+
"paws/labeled_final",
|
605 |
+
"paws/labeled_swap",
|
606 |
+
"medical_questions_pairs",
|
607 |
+
"conll2003/pos_tags",
|
608 |
+
"conll2003/chunk_tags",
|
609 |
+
"conll2003/ner_tags",
|
610 |
+
"hh-rlhf",
|
611 |
+
"model-written-evals",
|
612 |
+
"truthful_qa/multiple_choice",
|
613 |
+
"fig-qa",
|
614 |
+
"bigbench/analytic_entailment",
|
615 |
+
"bigbench/figure_of_speech_detection",
|
616 |
+
"bigbench/riddle_sense",
|
617 |
+
"bigbench/physical_intuition",
|
618 |
+
"bigbench/metaphor_boolean",
|
619 |
+
"bigbench/epistemic_reasoning",
|
620 |
+
"bigbench/dark_humor_detection",
|
621 |
+
"bigbench/international_phonetic_alphabet_nli",
|
622 |
+
"bigbench/arithmetic",
|
623 |
+
"bigbench/cifar10_classification",
|
624 |
+
"bigbench/hhh_alignment",
|
625 |
+
"bigbench/strategyqa",
|
626 |
+
"bigbench/play_dialog_same_or_different",
|
627 |
+
"bigbench/odd_one_out",
|
628 |
+
"bigbench/undo_permutation",
|
629 |
+
"bigbench/key_value_maps",
|
630 |
+
"bigbench/empirical_judgments",
|
631 |
+
"bigbench/question_selection",
|
632 |
+
"bigbench/date_understanding",
|
633 |
+
"bigbench/vitaminc_fact_verification",
|
634 |
+
"bigbench/cause_and_effect",
|
635 |
+
"bigbench/known_unknowns",
|
636 |
+
"bigbench/causal_judgment",
|
637 |
+
"bigbench/nonsense_words_grammar",
|
638 |
+
"bigbench/movie_dialog_same_or_different",
|
639 |
+
"bigbench/unit_interpretation",
|
640 |
+
"bigbench/abstract_narrative_understanding",
|
641 |
+
"bigbench/dyck_languages",
|
642 |
+
"bigbench/elementary_math_qa",
|
643 |
+
"bigbench/identify_math_theorems",
|
644 |
+
"bigbench/misconceptions",
|
645 |
+
"bigbench/crash_blossom",
|
646 |
+
"bigbench/novel_concepts",
|
647 |
+
"bigbench/social_iqa",
|
648 |
+
"bigbench/hindu_knowledge",
|
649 |
+
"bigbench/anachronisms",
|
650 |
+
"bigbench/cs_algorithms",
|
651 |
+
"bigbench/ruin_names",
|
652 |
+
"bigbench/phrase_relatedness",
|
653 |
+
"bigbench/crass_ai",
|
654 |
+
"bigbench/conceptual_combinations",
|
655 |
+
"bigbench/discourse_marker_prediction",
|
656 |
+
"bigbench/logic_grid_puzzle",
|
657 |
+
"bigbench/navigate",
|
658 |
+
"bigbench/emoji_movie",
|
659 |
+
"bigbench/implicit_relations",
|
660 |
+
"bigbench/presuppositions_as_nli",
|
661 |
+
"bigbench/code_line_description",
|
662 |
+
"bigbench/color",
|
663 |
+
"bigbench/gre_reading_comprehension",
|
664 |
+
"bigbench/physics",
|
665 |
+
"bigbench/symbol_interpretation",
|
666 |
+
"bigbench/tracking_shuffled_objects",
|
667 |
+
"bigbench/entailed_polarity",
|
668 |
+
"bigbench/mathematical_induction",
|
669 |
+
"bigbench/metaphor_understanding",
|
670 |
+
"bigbench/movie_recommendation",
|
671 |
+
"bigbench/simple_ethical_questions",
|
672 |
+
"bigbench/hyperbaton",
|
673 |
+
"bigbench/english_proverbs",
|
674 |
+
"bigbench/similarities_abstraction",
|
675 |
+
"bigbench/emojis_emotion_prediction",
|
676 |
+
"bigbench/temporal_sequences",
|
677 |
+
"bigbench/human_organs_senses",
|
678 |
+
"bigbench/penguins_in_a_table",
|
679 |
+
"bigbench/winowhy",
|
680 |
+
"bigbench/authorship_verification",
|
681 |
+
"bigbench/sentence_ambiguity",
|
682 |
+
"bigbench/mnist_ascii",
|
683 |
+
"bigbench/identify_odd_metaphor",
|
684 |
+
"bigbench/geometric_shapes",
|
685 |
+
"bigbench/evaluating_information_essentiality",
|
686 |
+
"bigbench/timedial",
|
687 |
+
"bigbench/salient_translation_error_detection",
|
688 |
+
"bigbench/suicide_risk",
|
689 |
+
"bigbench/fantasy_reasoning",
|
690 |
+
"bigbench/implicatures",
|
691 |
+
"bigbench/logical_sequence",
|
692 |
+
"bigbench/irony_identification",
|
693 |
+
"bigbench/formal_fallacies_syllogisms_negation",
|
694 |
+
"bigbench/understanding_fables",
|
695 |
+
"bigbench/logical_args",
|
696 |
+
"bigbench/analogical_similarity",
|
697 |
+
"bigbench/social_support",
|
698 |
+
"bigbench/logical_fallacy_detection",
|
699 |
+
"bigbench/bbq_lite_json",
|
700 |
+
"bigbench/reasoning_about_colored_objects",
|
701 |
+
"bigbench/intent_recognition",
|
702 |
+
"bigbench/contextual_parametric_knowledge_conflicts",
|
703 |
+
"bigbench/general_knowledge",
|
704 |
+
"bigbench/strange_stories",
|
705 |
+
"bigbench/sports_understanding",
|
706 |
+
"bigbench/checkmate_in_one",
|
707 |
+
"bigbench/moral_permissibility",
|
708 |
+
"bigbench/goal_step_wikihow",
|
709 |
+
"bigbench/snarks",
|
710 |
+
"bigbench/disambiguation_qa",
|
711 |
+
"bigbench/real_or_fake_text",
|
712 |
+
"bigbench/logical_deduction",
|
713 |
+
"bigbench/fact_checker",
|
714 |
+
"cos_e/v1.0",
|
715 |
+
"cosmos_qa",
|
716 |
+
"dream",
|
717 |
+
"openbookqa",
|
718 |
+
"qasc",
|
719 |
+
"quartz",
|
720 |
+
"quail",
|
721 |
+
"head_qa/en",
|
722 |
+
"sciq",
|
723 |
+
"social_i_qa",
|
724 |
+
"wiki_hop/original",
|
725 |
+
"wiqa",
|
726 |
+
"piqa",
|
727 |
+
"hellaswag",
|
728 |
+
"super_glue/copa",
|
729 |
+
"balanced-copa",
|
730 |
+
"e-CARE",
|
731 |
+
"art",
|
732 |
+
"winogrande/winogrande_xl",
|
733 |
+
"codah/codah",
|
734 |
+
"ai2_arc/ARC-Challenge/challenge",
|
735 |
+
"ai2_arc/ARC-Easy/challenge",
|
736 |
+
"definite_pronoun_resolution",
|
737 |
+
"swag/regular",
|
738 |
+
"math_qa",
|
739 |
+
"glue/cola",
|
740 |
+
"glue/sst2",
|
741 |
+
"utilitarianism",
|
742 |
+
"amazon_counterfactual/en",
|
743 |
+
"insincere-questions",
|
744 |
+
"toxic_conversations",
|
745 |
+
"TuringBench",
|
746 |
+
"trec",
|
747 |
+
"vitaminc/tals--vitaminc",
|
748 |
+
"hope_edi/english",
|
749 |
+
"rumoureval_2019/RumourEval2019",
|
750 |
+
"ethos/binary",
|
751 |
+
"ethos/multilabel",
|
752 |
+
"tweet_eval/stance_hillary",
|
753 |
+
"tweet_eval/stance_feminist",
|
754 |
+
"tweet_eval/stance_climate",
|
755 |
+
"tweet_eval/stance_atheism",
|
756 |
+
"tweet_eval/emoji",
|
757 |
+
"tweet_eval/sentiment",
|
758 |
+
"tweet_eval/offensive",
|
759 |
+
"tweet_eval/irony",
|
760 |
+
"tweet_eval/hate",
|
761 |
+
"tweet_eval/emotion",
|
762 |
+
"tweet_eval/stance_abortion",
|
763 |
+
"discovery/discovery",
|
764 |
+
"pragmeval/squinky-formality",
|
765 |
+
"pragmeval/squinky-implicature",
|
766 |
+
"pragmeval/emobank-dominance",
|
767 |
+
"pragmeval/squinky-informativeness",
|
768 |
+
"pragmeval/emobank-arousal",
|
769 |
+
"pragmeval/switchboard",
|
770 |
+
"pragmeval/mrda",
|
771 |
+
"pragmeval/verifiability",
|
772 |
+
"pragmeval/emobank-valence",
|
773 |
+
"pragmeval/emergent",
|
774 |
+
"pragmeval/gum",
|
775 |
+
"pragmeval/stac",
|
776 |
+
"pragmeval/persuasiveness-eloquence",
|
777 |
+
"pragmeval/persuasiveness-premisetype",
|
778 |
+
"pragmeval/persuasiveness-relevance",
|
779 |
+
"pragmeval/persuasiveness-specificity",
|
780 |
+
"pragmeval/persuasiveness-strength",
|
781 |
+
"pragmeval/sarcasm",
|
782 |
+
"pragmeval/persuasiveness-claimtype",
|
783 |
+
"pragmeval/pdtb",
|
784 |
+
"silicone/iemocap",
|
785 |
+
"silicone/sem",
|
786 |
+
"silicone/oasis",
|
787 |
+
"silicone/meld_s",
|
788 |
+
"silicone/meld_e",
|
789 |
+
"silicone/maptask",
|
790 |
+
"silicone/dyda_e",
|
791 |
+
"silicone/dyda_da",
|
792 |
+
"lex_glue/eurlex",
|
793 |
+
"lex_glue/scotus",
|
794 |
+
"lex_glue/ledgar",
|
795 |
+
"lex_glue/unfair_tos",
|
796 |
+
"lex_glue/case_hold",
|
797 |
+
"language-identification",
|
798 |
+
"imdb",
|
799 |
+
"rotten_tomatoes",
|
800 |
+
"ag_news",
|
801 |
+
"yelp_review_full/yelp_review_full",
|
802 |
+
"financial_phrasebank/sentences_allagree",
|
803 |
+
"poem_sentiment",
|
804 |
+
"dbpedia_14/dbpedia_14",
|
805 |
+
"amazon_polarity/amazon_polarity",
|
806 |
+
"app_reviews",
|
807 |
+
"hate_speech18",
|
808 |
+
"sms_spam",
|
809 |
+
"humicroedit/subtask-1",
|
810 |
+
"humicroedit/subtask-2",
|
811 |
+
"snips_built_in_intents",
|
812 |
+
"hate_speech_offensive",
|
813 |
+
"yahoo_answers_topics",
|
814 |
+
"stackoverflow-questions",
|
815 |
+
"hyperpartisan_news",
|
816 |
+
"sciie",
|
817 |
+
"citation_intent",
|
818 |
+
"go_emotions/simplified",
|
819 |
+
"scicite",
|
820 |
+
"liar",
|
821 |
+
"lexical_relation_classification/K&H+N",
|
822 |
+
"lexical_relation_classification/CogALexV",
|
823 |
+
"lexical_relation_classification/BLESS",
|
824 |
+
"lexical_relation_classification/ROOT09",
|
825 |
+
"lexical_relation_classification/EVALution",
|
826 |
+
"linguisticprobing/bigram_shift",
|
827 |
+
"linguisticprobing/top_constituents",
|
828 |
+
"linguisticprobing/subj_number",
|
829 |
+
"linguisticprobing/odd_man_out",
|
830 |
+
"linguisticprobing/tree_depth",
|
831 |
+
"linguisticprobing/past_present",
|
832 |
+
"linguisticprobing/sentence_length",
|
833 |
+
"linguisticprobing/obj_number",
|
834 |
+
"linguisticprobing/coordination_inversion",
|
835 |
+
"crowdflower/political-media-audience",
|
836 |
+
"crowdflower/text_emotion",
|
837 |
+
"crowdflower/economic-news",
|
838 |
+
"crowdflower/corporate-messaging",
|
839 |
+
"crowdflower/airline-sentiment",
|
840 |
+
"crowdflower/tweet_global_warming",
|
841 |
+
"crowdflower/sentiment_nuclear_power",
|
842 |
+
"crowdflower/political-media-bias",
|
843 |
+
"crowdflower/political-media-message",
|
844 |
+
"ethics/commonsense",
|
845 |
+
"ethics/deontology",
|
846 |
+
"ethics/justice",
|
847 |
+
"ethics/virtue",
|
848 |
+
"emo/emo2019",
|
849 |
+
"google_wellformed_query",
|
850 |
+
"tweets_hate_speech_detection",
|
851 |
+
"has_part",
|
852 |
+
"wnut_17/wnut_17",
|
853 |
+
"ncbi_disease/ncbi_disease",
|
854 |
+
"acronym_identification",
|
855 |
+
"jnlpba/jnlpba",
|
856 |
+
"ontonotes_english/SpeedOfMagic--ontonotes_english",
|
857 |
+
"blog_authorship_corpus/gender",
|
858 |
+
"blog_authorship_corpus/age",
|
859 |
+
"blog_authorship_corpus/horoscope",
|
860 |
+
"blog_authorship_corpus/job",
|
861 |
+
"open_question_type",
|
862 |
+
"health_fact",
|
863 |
+
"commonsense_qa",
|
864 |
+
"mc_taco",
|
865 |
+
"ade_corpus_v2/Ade_corpus_v2_classification",
|
866 |
+
"discosense",
|
867 |
+
"circa",
|
868 |
+
"phrase_similarity",
|
869 |
+
"scientific-exaggeration-detection",
|
870 |
+
"quarel",
|
871 |
+
"fever-evidence-related/mwong--fever-related",
|
872 |
+
"numer_sense",
|
873 |
+
"dynasent/dynabench.dynasent.r1.all/r1",
|
874 |
+
"dynasent/dynabench.dynasent.r2.all/r2",
|
875 |
+
"Sarcasm_News_Headline",
|
876 |
+
"sem_eval_2010_task_8",
|
877 |
+
"auditor_review/demo-org--auditor_review",
|
878 |
+
"medmcqa",
|
879 |
+
"Dynasent_Disagreement",
|
880 |
+
"Politeness_Disagreement",
|
881 |
+
"SBIC_Disagreement",
|
882 |
+
"SChem_Disagreement",
|
883 |
+
"Dilemmas_Disagreement",
|
884 |
+
"logiqa",
|
885 |
+
"wiki_qa",
|
886 |
+
"cycic_classification",
|
887 |
+
"cycic_multiplechoice",
|
888 |
+
"sts-companion",
|
889 |
+
"commonsense_qa_2.0",
|
890 |
+
"lingnli",
|
891 |
+
"monotonicity-entailment",
|
892 |
+
"arct",
|
893 |
+
"scinli",
|
894 |
+
"naturallogic",
|
895 |
+
"onestop_qa",
|
896 |
+
"moral_stories/full",
|
897 |
+
"prost",
|
898 |
+
"dynahate",
|
899 |
+
"syntactic-augmentation-nli",
|
900 |
+
"autotnli",
|
901 |
+
"CONDAQA",
|
902 |
+
"webgpt_comparisons",
|
903 |
+
"synthetic-instruct-gptj-pairwise",
|
904 |
+
"scruples",
|
905 |
+
"wouldyourather",
|
906 |
+
"attempto-nli",
|
907 |
+
"defeasible-nli/atomic",
|
908 |
+
"defeasible-nli/snli",
|
909 |
+
"help-nli",
|
910 |
+
"nli-veridicality-transitivity",
|
911 |
+
"natural-language-satisfiability",
|
912 |
+
"lonli",
|
913 |
+
"dadc-limit-nli",
|
914 |
+
"FLUTE",
|
915 |
+
"strategy-qa",
|
916 |
+
"summarize_from_feedback/comparisons",
|
917 |
+
"folio",
|
918 |
+
"tomi-nli",
|
919 |
+
"avicenna",
|
920 |
+
"SHP",
|
921 |
+
"MedQA-USMLE-4-options-hf",
|
922 |
+
"wikimedqa/medwiki",
|
923 |
+
"cicero",
|
924 |
+
"CREAK",
|
925 |
+
"mutual",
|
926 |
+
"NeQA",
|
927 |
+
"quote-repetition",
|
928 |
+
"redefine-math",
|
929 |
+
"puzzte",
|
930 |
+
"implicatures",
|
931 |
+
"race/middle",
|
932 |
+
"race/high",
|
933 |
+
"race-c",
|
934 |
+
"spartqa-yn",
|
935 |
+
"spartqa-mchoice",
|
936 |
+
"temporal-nli",
|
937 |
+
"riddle_sense",
|
938 |
+
"clcd-english",
|
939 |
+
"twentyquestions",
|
940 |
+
"reclor",
|
941 |
+
"counterfactually-augmented-imdb",
|
942 |
+
"counterfactually-augmented-snli",
|
943 |
+
"cnli",
|
944 |
+
"boolq-natural-perturbations",
|
945 |
+
"acceptability-prediction",
|
946 |
+
"equate",
|
947 |
+
"ScienceQA_text_only",
|
948 |
+
"ekar_english",
|
949 |
+
"implicit-hate-stg1",
|
950 |
+
"chaos-mnli-ambiguity",
|
951 |
+
"headline_cause/en_simple",
|
952 |
+
"logiqa-2.0-nli",
|
953 |
+
"oasst1_dense_flat/quality",
|
954 |
+
"oasst1_dense_flat/toxicity",
|
955 |
+
"oasst1_dense_flat/helpfulness",
|
956 |
+
"PARARULE-Plus",
|
957 |
+
"mindgames",
|
958 |
+
"universal_dependencies/en_ewt/deprel",
|
959 |
+
"universal_dependencies/en_lines/deprel",
|
960 |
+
"universal_dependencies/en_partut/deprel",
|
961 |
+
"universal_dependencies/en_gum/deprel",
|
962 |
+
"ambient",
|
963 |
+
"path-naturalness-prediction",
|
964 |
+
"civil_comments/toxicity",
|
965 |
+
"civil_comments/severe_toxicity",
|
966 |
+
"civil_comments/obscene",
|
967 |
+
"civil_comments/threat",
|
968 |
+
"civil_comments/insult",
|
969 |
+
"civil_comments/identity_attack",
|
970 |
+
"civil_comments/sexual_explicit",
|
971 |
+
"cloth",
|
972 |
+
"dgen",
|
973 |
+
"oasst1_pairwise_rlhf_reward",
|
974 |
+
"I2D2",
|
975 |
+
"args_me",
|
976 |
+
"Touche23-ValueEval",
|
977 |
+
"starcon",
|
978 |
+
"banking77",
|
979 |
+
"ruletaker",
|
980 |
+
"lsat_qa/all",
|
981 |
+
"ConTRoL-nli",
|
982 |
+
"tracie",
|
983 |
+
"sherliic",
|
984 |
+
"sen-making/1",
|
985 |
+
"sen-making/2",
|
986 |
+
"winowhy",
|
987 |
+
"mbib-base/cognitive-bias",
|
988 |
+
"mbib-base/fake-news",
|
989 |
+
"mbib-base/gender-bias",
|
990 |
+
"mbib-base/hate-speech",
|
991 |
+
"mbib-base/linguistic-bias",
|
992 |
+
"mbib-base/political-bias",
|
993 |
+
"mbib-base/racial-bias",
|
994 |
+
"mbib-base/text-level-bias",
|
995 |
+
"robustLR",
|
996 |
+
"v1/gen_train234_test2to10",
|
997 |
+
"logical-fallacy",
|
998 |
+
"parade",
|
999 |
+
"cladder",
|
1000 |
+
"subjectivity",
|
1001 |
+
"MOH",
|
1002 |
+
"VUAC",
|
1003 |
+
"TroFi",
|
1004 |
+
"sharc_modified/mod",
|
1005 |
+
"conceptrules_v2",
|
1006 |
+
"disrpt/eng.dep.scidtb",
|
1007 |
+
"conll2000",
|
1008 |
+
"few-nerd/supervised",
|
1009 |
+
"finer-139",
|
1010 |
+
"zero-shot-label-nli",
|
1011 |
+
"com2sense",
|
1012 |
+
"scone",
|
1013 |
+
"winodict",
|
1014 |
+
"fool-me-twice",
|
1015 |
+
"monli",
|
1016 |
+
"corr2cause",
|
1017 |
+
"lsat_qa/all",
|
1018 |
+
"apt",
|
1019 |
+
"twitter-financial-news-sentiment",
|
1020 |
+
"icl-symbol-tuning-instruct",
|
1021 |
+
"SpaceNLI",
|
1022 |
+
"propsegment/nli",
|
1023 |
+
"HatemojiBuild",
|
1024 |
+
"regset",
|
1025 |
+
"esci",
|
1026 |
+
"chatbot_arena_conversations",
|
1027 |
+
"dnd_style_intents",
|
1028 |
+
"babi_nli",
|
1029 |
+
"gen_debiased_nli",
|
1030 |
+
"imppres/presupposition",
|
1031 |
+
"/prag",
|
1032 |
+
"blimp-2",
|
1033 |
+
"mmlu-4"
|
1034 |
+
],
|
1035 |
+
"torch_dtype": "float32",
|
1036 |
+
"transformers_version": "4.26.1",
|
1037 |
+
"type_vocab_size": 0,
|
1038 |
+
"vocab_size": 128100
|
1039 |
+
}
|
gitattributes.txt
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d58b81ba665995176104a66f7b7d0b9e2e412564f6b33917e84c4eb920946841
|
3 |
+
size 737726552
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e28518532d77001e5030110c5761ec75499fc5fad1a7e81045c7ce0ba0a86e3
|
3 |
+
size 737771833
|
special_tokens_map.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
9 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tasks.md
ADDED
@@ -0,0 +1,444 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- 0 babi_nli/counting
|
2 |
+
- 1 babi_nli/indefinite-knowledge
|
3 |
+
- 2 babi_nli/simple-negation
|
4 |
+
- 3 babi_nli/three-arg-relations
|
5 |
+
- 4 babi_nli/basic-induction
|
6 |
+
- 5 babi_nli/time-reasoning
|
7 |
+
- 6 babi_nli/compound-coreference
|
8 |
+
- 7 babi_nli/path-finding
|
9 |
+
- 8 babi_nli/positional-reasoning
|
10 |
+
- 9 babi_nli/conjunction
|
11 |
+
- 10 babi_nli/size-reasoning
|
12 |
+
- 11 babi_nli/yes-no-questions
|
13 |
+
- 12 babi_nli/basic-coreference
|
14 |
+
- 13 babi_nli/two-supporting-facts
|
15 |
+
- 14 babi_nli/lists-sets
|
16 |
+
- 15 babi_nli/two-arg-relations
|
17 |
+
- 16 babi_nli/three-supporting-facts
|
18 |
+
- 17 babi_nli/basic-deduction
|
19 |
+
- 18 babi_nli/single-supporting-fact
|
20 |
+
- 19 anli/a1
|
21 |
+
- 20 anli/a2
|
22 |
+
- 21 anli/a3
|
23 |
+
- 22 sick/label
|
24 |
+
- 23 sick/relatedness
|
25 |
+
- 24 sick/entailment_AB
|
26 |
+
- 25 sick/entailment_BA
|
27 |
+
- 26 snli
|
28 |
+
- 27 scitail/snli_format
|
29 |
+
- 28 hans
|
30 |
+
- 29 WANLI
|
31 |
+
- 30 recast/recast_kg_relations
|
32 |
+
- 31 recast/recast_puns
|
33 |
+
- 32 recast/recast_factuality
|
34 |
+
- 33 recast/recast_megaveridicality
|
35 |
+
- 34 recast/recast_verbcorner
|
36 |
+
- 35 recast/recast_verbnet
|
37 |
+
- 36 recast/recast_ner
|
38 |
+
- 37 recast/recast_sentiment
|
39 |
+
- 38 probability_words_nli/usnli
|
40 |
+
- 39 probability_words_nli/reasoning_1hop
|
41 |
+
- 40 probability_words_nli/reasoning_2hop
|
42 |
+
- 41 nan-nli/joey234--nan-nli
|
43 |
+
- 42 nli_fever
|
44 |
+
- 43 breaking_nli
|
45 |
+
- 44 conj_nli
|
46 |
+
- 45 fracas
|
47 |
+
- 46 dialogue_nli
|
48 |
+
- 47 mpe
|
49 |
+
- 48 dnc
|
50 |
+
- 49 gpt3_nli
|
51 |
+
- 50 recast_white/fnplus
|
52 |
+
- 51 recast_white/sprl
|
53 |
+
- 52 recast_white/dpr
|
54 |
+
- 53 joci
|
55 |
+
- 54 contrast_nli
|
56 |
+
- 55 robust_nli/IS_CS
|
57 |
+
- 56 robust_nli/LI_LI
|
58 |
+
- 57 robust_nli/ST_WO
|
59 |
+
- 58 robust_nli/PI_SP
|
60 |
+
- 59 robust_nli/PI_CD
|
61 |
+
- 60 robust_nli/ST_SE
|
62 |
+
- 61 robust_nli/ST_NE
|
63 |
+
- 62 robust_nli/ST_LM
|
64 |
+
- 63 robust_nli_is_sd
|
65 |
+
- 64 robust_nli_li_ts
|
66 |
+
- 65 gen_debiased_nli/snli_seq_z
|
67 |
+
- 66 gen_debiased_nli/snli_z_aug
|
68 |
+
- 67 gen_debiased_nli/snli_par_z
|
69 |
+
- 68 gen_debiased_nli/mnli_par_z
|
70 |
+
- 69 gen_debiased_nli/mnli_z_aug
|
71 |
+
- 70 gen_debiased_nli/mnli_seq_z
|
72 |
+
- 71 add_one_rte
|
73 |
+
- 72 imppres/presupposition_cleft_uniqueness/presupposition
|
74 |
+
- 73 imppres/presupposition_possessed_definites_uniqueness/presupposition
|
75 |
+
- 74 imppres/presupposition_possessed_definites_existence/presupposition
|
76 |
+
- 75 imppres/presupposition_only_presupposition/presupposition
|
77 |
+
- 76 imppres/presupposition_all_n_presupposition/presupposition
|
78 |
+
- 77 imppres/presupposition_both_presupposition/presupposition
|
79 |
+
- 78 imppres/presupposition_change_of_state/presupposition
|
80 |
+
- 79 imppres/presupposition_cleft_existence/presupposition
|
81 |
+
- 80 imppres/presupposition_question_presupposition/presupposition
|
82 |
+
- 81 imppres/implicature_modals/prag
|
83 |
+
- 82 imppres/implicature_numerals_10_100/prag
|
84 |
+
- 83 imppres/implicature_numerals_2_3/prag
|
85 |
+
- 84 imppres/implicature_gradable_adjective/prag
|
86 |
+
- 85 imppres/implicature_quantifiers/prag
|
87 |
+
- 86 imppres/implicature_gradable_verb/prag
|
88 |
+
- 87 imppres/implicature_connectives/prag
|
89 |
+
- 88 imppres/implicature_gradable_adjective/log
|
90 |
+
- 89 imppres/implicature_gradable_verb/log
|
91 |
+
- 90 imppres/implicature_numerals_2_3/log
|
92 |
+
- 91 imppres/implicature_numerals_10_100/log
|
93 |
+
- 92 imppres/implicature_modals/log
|
94 |
+
- 93 imppres/implicature_quantifiers/log
|
95 |
+
- 94 imppres/implicature_connectives/log
|
96 |
+
- 95 glue_diagnostics/diagnostics
|
97 |
+
- 96 hlgd
|
98 |
+
- 97 paws/labeled_final
|
99 |
+
- 98 paws/labeled_swap
|
100 |
+
- 99 quora
|
101 |
+
- 100 medical_questions_pairs
|
102 |
+
- 101 conll2003/pos_tags
|
103 |
+
- 102 conll2003/chunk_tags
|
104 |
+
- 103 conll2003/ner_tags
|
105 |
+
- 104 hh-rlhf
|
106 |
+
- 105 model-written-evals
|
107 |
+
- 106 truthful_qa/multiple_choice
|
108 |
+
- 107 fig-qa
|
109 |
+
- 108 bigbench/fantasy_reasoning
|
110 |
+
- 109 bigbench/nonsense_words_grammar
|
111 |
+
- 110 bigbench/analytic_entailment
|
112 |
+
- 111 bigbench/logic_grid_puzzle
|
113 |
+
- 112 bigbench/geometric_shapes
|
114 |
+
- 113 bigbench/key_value_maps
|
115 |
+
- 114 bigbench/analogical_similarity
|
116 |
+
- 115 bigbench/metaphor_understanding
|
117 |
+
- 116 bigbench/metaphor_boolean
|
118 |
+
- 117 bigbench/ruin_names
|
119 |
+
- 118 bigbench/cs_algorithms
|
120 |
+
- 119 bigbench/physical_intuition
|
121 |
+
- 120 bigbench/mnist_ascii
|
122 |
+
- 121 bigbench/moral_permissibility
|
123 |
+
- 122 bigbench/emoji_movie
|
124 |
+
- 123 bigbench/snarks
|
125 |
+
- 124 bigbench/timedial
|
126 |
+
- 125 bigbench/dark_humor_detection
|
127 |
+
- 126 bigbench/gre_reading_comprehension
|
128 |
+
- 127 bigbench/empirical_judgments
|
129 |
+
- 128 bigbench/causal_judgment
|
130 |
+
- 129 bigbench/fact_checker
|
131 |
+
- 130 bigbench/logical_fallacy_detection
|
132 |
+
- 131 bigbench/identify_math_theorems
|
133 |
+
- 132 bigbench/dyck_languages
|
134 |
+
- 133 bigbench/winowhy
|
135 |
+
- 134 bigbench/logical_sequence
|
136 |
+
- 135 bigbench/strategyqa
|
137 |
+
- 136 bigbench/unit_interpretation
|
138 |
+
- 137 bigbench/authorship_verification
|
139 |
+
- 138 bigbench/undo_permutation
|
140 |
+
- 139 bigbench/epistemic_reasoning
|
141 |
+
- 140 bigbench/human_organs_senses
|
142 |
+
- 141 bigbench/misconceptions
|
143 |
+
- 142 bigbench/international_phonetic_alphabet_nli
|
144 |
+
- 143 bigbench/identify_odd_metaphor
|
145 |
+
- 144 bigbench/mathematical_induction
|
146 |
+
- 145 bigbench/odd_one_out
|
147 |
+
- 146 bigbench/reasoning_about_colored_objects
|
148 |
+
- 147 bigbench/strange_stories
|
149 |
+
- 148 bigbench/evaluating_information_essentiality
|
150 |
+
- 149 bigbench/figure_of_speech_detection
|
151 |
+
- 150 bigbench/english_proverbs
|
152 |
+
- 151 bigbench/general_knowledge
|
153 |
+
- 152 bigbench/tracking_shuffled_objects
|
154 |
+
- 153 bigbench/physics
|
155 |
+
- 154 bigbench/anachronisms
|
156 |
+
- 155 bigbench/simple_ethical_questions
|
157 |
+
- 156 bigbench/logical_args
|
158 |
+
- 157 bigbench/suicide_risk
|
159 |
+
- 158 bigbench/sentence_ambiguity
|
160 |
+
- 159 bigbench/temporal_sequences
|
161 |
+
- 160 bigbench/penguins_in_a_table
|
162 |
+
- 161 bigbench/sports_understanding
|
163 |
+
- 162 bigbench/hyperbaton
|
164 |
+
- 163 bigbench/code_line_description
|
165 |
+
- 164 bigbench/question_selection
|
166 |
+
- 165 bigbench/disambiguation_qa
|
167 |
+
- 166 bigbench/date_understanding
|
168 |
+
- 167 bigbench/play_dialog_same_or_different
|
169 |
+
- 168 bigbench/salient_translation_error_detection
|
170 |
+
- 169 bigbench/irony_identification
|
171 |
+
- 170 bigbench/emojis_emotion_prediction
|
172 |
+
- 171 bigbench/hindu_knowledge
|
173 |
+
- 172 bigbench/conceptual_combinations
|
174 |
+
- 173 bigbench/implicatures
|
175 |
+
- 174 bigbench/movie_dialog_same_or_different
|
176 |
+
- 175 bigbench/social_support
|
177 |
+
- 176 bigbench/presuppositions_as_nli
|
178 |
+
- 177 bigbench/vitaminc_fact_verification
|
179 |
+
- 178 bigbench/hhh_alignment
|
180 |
+
- 179 bigbench/implicit_relations
|
181 |
+
- 180 bigbench/bbq_lite_json
|
182 |
+
- 181 bigbench/phrase_relatedness
|
183 |
+
- 182 bigbench/logical_deduction
|
184 |
+
- 183 bigbench/discourse_marker_prediction
|
185 |
+
- 184 bigbench/movie_recommendation
|
186 |
+
- 185 bigbench/real_or_fake_text
|
187 |
+
- 186 bigbench/formal_fallacies_syllogisms_negation
|
188 |
+
- 187 bigbench/crass_ai
|
189 |
+
- 188 blimp/inchoative
|
190 |
+
- 189 blimp/principle_A_c_command
|
191 |
+
- 190 blimp/matrix_question_npi_licensor_present
|
192 |
+
- 191 blimp/wh_questions_subject_gap_long_distance
|
193 |
+
- 192 blimp/sentential_subject_island
|
194 |
+
- 193 blimp/existential_there_quantifiers_2
|
195 |
+
- 194 blimp/sentential_negation_npi_scope
|
196 |
+
- 195 blimp/complex_NP_island
|
197 |
+
- 196 blimp/principle_A_reconstruction
|
198 |
+
- 197 blimp/animate_subject_passive
|
199 |
+
- 198 blimp/tough_vs_raising_1
|
200 |
+
- 199 blimp/wh_vs_that_with_gap
|
201 |
+
- 200 blimp/principle_A_domain_2
|
202 |
+
- 201 blimp/npi_present_1
|
203 |
+
- 202 blimp/wh_vs_that_with_gap_long_distance
|
204 |
+
- 203 blimp/superlative_quantifiers_1
|
205 |
+
- 204 blimp/npi_present_2
|
206 |
+
- 205 blimp/wh_questions_object_gap
|
207 |
+
- 206 blimp/coordinate_structure_constraint_complex_left_branch
|
208 |
+
- 207 blimp/coordinate_structure_constraint_object_extraction
|
209 |
+
- 208 blimp/left_branch_island_echo_question
|
210 |
+
- 209 blimp/drop_argument
|
211 |
+
- 210 cos_e/v1.0
|
212 |
+
- 211 cosmos_qa
|
213 |
+
- 212 dream
|
214 |
+
- 213 openbookqa
|
215 |
+
- 214 qasc
|
216 |
+
- 215 quartz
|
217 |
+
- 216 quail
|
218 |
+
- 217 head_qa/en
|
219 |
+
- 218 sciq
|
220 |
+
- 219 social_i_qa
|
221 |
+
- 220 wiki_hop
|
222 |
+
- 221 wiqa
|
223 |
+
- 222 piqa
|
224 |
+
- 223 hellaswag
|
225 |
+
- 224 super_glue/copa
|
226 |
+
- 225 art
|
227 |
+
- 226 hendrycks_test/moral_disputes
|
228 |
+
- 227 hendrycks_test/moral_scenarios
|
229 |
+
- 228 hendrycks_test/nutrition
|
230 |
+
- 229 hendrycks_test/philosophy
|
231 |
+
- 230 hendrycks_test/prehistory
|
232 |
+
- 231 hendrycks_test/professional_accounting
|
233 |
+
- 232 hendrycks_test/professional_law
|
234 |
+
- 233 hendrycks_test/world_religions
|
235 |
+
- 234 hendrycks_test/professional_psychology
|
236 |
+
- 235 hendrycks_test/public_relations
|
237 |
+
- 236 hendrycks_test/security_studies
|
238 |
+
- 237 hendrycks_test/sociology
|
239 |
+
- 238 hendrycks_test/us_foreign_policy
|
240 |
+
- 239 hendrycks_test/virology
|
241 |
+
- 240 hendrycks_test/miscellaneous
|
242 |
+
- 241 hendrycks_test/professional_medicine
|
243 |
+
- 242 hendrycks_test/medical_genetics
|
244 |
+
- 243 hendrycks_test/college_mathematics
|
245 |
+
- 244 hendrycks_test/management
|
246 |
+
- 245 hendrycks_test/high_school_computer_science
|
247 |
+
- 246 hendrycks_test/astronomy
|
248 |
+
- 247 hendrycks_test/high_school_chemistry
|
249 |
+
- 248 hendrycks_test/high_school_biology
|
250 |
+
- 249 hendrycks_test/global_facts
|
251 |
+
- 250 hendrycks_test/formal_logic
|
252 |
+
- 251 hendrycks_test/elementary_mathematics
|
253 |
+
- 252 hendrycks_test/high_school_european_history
|
254 |
+
- 253 hendrycks_test/electrical_engineering
|
255 |
+
- 254 hendrycks_test/conceptual_physics
|
256 |
+
- 255 hendrycks_test/computer_security
|
257 |
+
- 256 hendrycks_test/college_physics
|
258 |
+
- 257 hendrycks_test/college_medicine
|
259 |
+
- 258 hendrycks_test/college_computer_science
|
260 |
+
- 259 hendrycks_test/college_chemistry
|
261 |
+
- 260 hendrycks_test/college_biology
|
262 |
+
- 261 hendrycks_test/econometrics
|
263 |
+
- 262 hendrycks_test/clinical_knowledge
|
264 |
+
- 263 hendrycks_test/anatomy
|
265 |
+
- 264 hendrycks_test/marketing
|
266 |
+
- 265 hendrycks_test/machine_learning
|
267 |
+
- 266 hendrycks_test/logical_fallacies
|
268 |
+
- 267 hendrycks_test/jurisprudence
|
269 |
+
- 268 hendrycks_test/international_law
|
270 |
+
- 269 hendrycks_test/human_sexuality
|
271 |
+
- 270 hendrycks_test/human_aging
|
272 |
+
- 271 hendrycks_test/high_school_world_history
|
273 |
+
- 272 hendrycks_test/abstract_algebra
|
274 |
+
- 273 hendrycks_test/high_school_us_history
|
275 |
+
- 274 hendrycks_test/high_school_psychology
|
276 |
+
- 275 hendrycks_test/high_school_physics
|
277 |
+
- 276 hendrycks_test/high_school_microeconomics
|
278 |
+
- 277 hendrycks_test/high_school_mathematics
|
279 |
+
- 278 hendrycks_test/high_school_macroeconomics
|
280 |
+
- 279 hendrycks_test/high_school_government_and_politics
|
281 |
+
- 280 hendrycks_test/high_school_geography
|
282 |
+
- 281 hendrycks_test/high_school_statistics
|
283 |
+
- 282 hendrycks_test/business_ethics
|
284 |
+
- 283 winogrande/winogrande_xl
|
285 |
+
- 284 codah/codah
|
286 |
+
- 285 ai2_arc/ARC-Challenge/challenge
|
287 |
+
- 286 ai2_arc/ARC-Easy/challenge
|
288 |
+
- 287 definite_pronoun_resolution
|
289 |
+
- 288 swag
|
290 |
+
- 289 math_qa
|
291 |
+
- 290 utilitarianism
|
292 |
+
- 291 TuringBench
|
293 |
+
- 292 trec
|
294 |
+
- 293 vitaminc/tals--vitaminc
|
295 |
+
- 294 hope_edi/english
|
296 |
+
- 295 rumoureval_2019/RumourEval2019
|
297 |
+
- 296 ethos/binary
|
298 |
+
- 297 ethos/multilabel
|
299 |
+
- 298 glue/cola
|
300 |
+
- 299 glue/sst2
|
301 |
+
- 300 glue/mrpc
|
302 |
+
- 301 glue/qqp
|
303 |
+
- 302 glue/stsb
|
304 |
+
- 303 glue/mnli
|
305 |
+
- 304 glue/qnli
|
306 |
+
- 305 glue/rte
|
307 |
+
- 306 glue/wnli
|
308 |
+
- 307 super_glue/boolq
|
309 |
+
- 308 super_glue/cb
|
310 |
+
- 309 super_glue/multirc
|
311 |
+
- 310 super_glue/wic
|
312 |
+
- 311 super_glue/axg
|
313 |
+
- 312 tweet_eval/stance_feminist
|
314 |
+
- 313 tweet_eval/stance_atheism
|
315 |
+
- 314 tweet_eval/stance_hillary
|
316 |
+
- 315 tweet_eval/stance_abortion
|
317 |
+
- 316 tweet_eval/sentiment
|
318 |
+
- 317 tweet_eval/offensive
|
319 |
+
- 318 tweet_eval/stance_climate
|
320 |
+
- 319 tweet_eval/irony
|
321 |
+
- 320 tweet_eval/emotion
|
322 |
+
- 321 tweet_eval/emoji
|
323 |
+
- 322 tweet_eval/hate
|
324 |
+
- 323 discovery/discovery
|
325 |
+
- 324 pragmeval/switchboard
|
326 |
+
- 325 pragmeval/squinky-informativeness
|
327 |
+
- 326 pragmeval/emobank-arousal
|
328 |
+
- 327 pragmeval/emobank-dominance
|
329 |
+
- 328 pragmeval/emobank-valence
|
330 |
+
- 329 pragmeval/mrda
|
331 |
+
- 330 pragmeval/verifiability
|
332 |
+
- 331 pragmeval/squinky-implicature
|
333 |
+
- 332 pragmeval/squinky-formality
|
334 |
+
- 333 pragmeval/gum
|
335 |
+
- 334 pragmeval/emergent
|
336 |
+
- 335 pragmeval/persuasiveness-premisetype
|
337 |
+
- 336 pragmeval/pdtb
|
338 |
+
- 337 pragmeval/persuasiveness-eloquence
|
339 |
+
- 338 pragmeval/persuasiveness-specificity
|
340 |
+
- 339 pragmeval/persuasiveness-strength
|
341 |
+
- 340 pragmeval/sarcasm
|
342 |
+
- 341 pragmeval/stac
|
343 |
+
- 342 pragmeval/persuasiveness-claimtype
|
344 |
+
- 343 pragmeval/persuasiveness-relevance
|
345 |
+
- 344 lex_glue/eurlex
|
346 |
+
- 345 lex_glue/scotus
|
347 |
+
- 346 lex_glue/ledgar
|
348 |
+
- 347 lex_glue/unfair_tos
|
349 |
+
- 348 lex_glue/case_hold
|
350 |
+
- 349 imdb
|
351 |
+
- 350 rotten_tomatoes
|
352 |
+
- 351 ag_news
|
353 |
+
- 352 yelp_review_full/yelp_review_full
|
354 |
+
- 353 financial_phrasebank/sentences_allagree
|
355 |
+
- 354 poem_sentiment
|
356 |
+
- 355 dbpedia_14/dbpedia_14
|
357 |
+
- 356 amazon_polarity/amazon_polarity
|
358 |
+
- 357 app_reviews
|
359 |
+
- 358 hate_speech18
|
360 |
+
- 359 sms_spam
|
361 |
+
- 360 humicroedit/subtask-1
|
362 |
+
- 361 humicroedit/subtask-2
|
363 |
+
- 362 snips_built_in_intents
|
364 |
+
- 363 banking77
|
365 |
+
- 364 hate_speech_offensive
|
366 |
+
- 365 hyperpartisan_news_detection/byarticle
|
367 |
+
- 366 hyperpartisan_news_detection/bypublisher
|
368 |
+
- 367 go_emotions/simplified
|
369 |
+
- 368 scicite
|
370 |
+
- 369 liar
|
371 |
+
- 370 lexical_relation_classification/ROOT09
|
372 |
+
- 371 lexical_relation_classification/EVALution
|
373 |
+
- 372 lexical_relation_classification/CogALexV
|
374 |
+
- 373 lexical_relation_classification/BLESS
|
375 |
+
- 374 lexical_relation_classification/K&H+N
|
376 |
+
- 375 linguisticprobing/coordination_inversion
|
377 |
+
- 376 linguisticprobing/odd_man_out
|
378 |
+
- 377 linguisticprobing/word_content
|
379 |
+
- 378 linguisticprobing/obj_number
|
380 |
+
- 379 linguisticprobing/past_present
|
381 |
+
- 380 linguisticprobing/tree_depth
|
382 |
+
- 381 linguisticprobing/sentence_length
|
383 |
+
- 382 linguisticprobing/top_constituents
|
384 |
+
- 383 linguisticprobing/bigram_shift
|
385 |
+
- 384 linguisticprobing/subj_number
|
386 |
+
- 385 crowdflower/sentiment_nuclear_power
|
387 |
+
- 386 crowdflower/tweet_global_warming
|
388 |
+
- 387 crowdflower/airline-sentiment
|
389 |
+
- 388 crowdflower/economic-news
|
390 |
+
- 389 crowdflower/political-media-audience
|
391 |
+
- 390 crowdflower/political-media-bias
|
392 |
+
- 391 crowdflower/political-media-message
|
393 |
+
- 392 crowdflower/text_emotion
|
394 |
+
- 393 crowdflower/corporate-messaging
|
395 |
+
- 394 ethics/commonsense
|
396 |
+
- 395 ethics/deontology
|
397 |
+
- 396 ethics/justice
|
398 |
+
- 397 ethics/virtue
|
399 |
+
- 398 emo/emo2019
|
400 |
+
- 399 google_wellformed_query
|
401 |
+
- 400 tweets_hate_speech_detection
|
402 |
+
- 401 adv_glue/adv_sst2
|
403 |
+
- 402 adv_glue/adv_qqp
|
404 |
+
- 403 adv_glue/adv_mnli
|
405 |
+
- 404 adv_glue/adv_mnli_mismatched
|
406 |
+
- 405 adv_glue/adv_qnli
|
407 |
+
- 406 adv_glue/adv_rte
|
408 |
+
- 407 has_part
|
409 |
+
- 408 wnut_17/wnut_17
|
410 |
+
- 409 ncbi_disease/ncbi_disease
|
411 |
+
- 410 acronym_identification
|
412 |
+
- 411 jnlpba/jnlpba
|
413 |
+
- 412 species_800/species_800
|
414 |
+
- 413 ontonotes_english/SpeedOfMagic--ontonotes_english
|
415 |
+
- 414 blog_authorship_corpus/gender
|
416 |
+
- 415 blog_authorship_corpus/age
|
417 |
+
- 416 blog_authorship_corpus/horoscope
|
418 |
+
- 417 blog_authorship_corpus/job
|
419 |
+
- 418 open_question_type
|
420 |
+
- 419 health_fact
|
421 |
+
- 420 commonsense_qa
|
422 |
+
- 421 mc_taco
|
423 |
+
- 422 ade_corpus_v2/Ade_corpus_v2_classification
|
424 |
+
- 423 discosense
|
425 |
+
- 424 circa
|
426 |
+
- 425 code_x_glue_cc_defect_detection
|
427 |
+
- 426 code_x_glue_cc_clone_detection_big_clone_bench
|
428 |
+
- 427 code_x_glue_cc_code_refinement/medium
|
429 |
+
- 428 EffectiveFeedbackStudentWriting
|
430 |
+
- 429 promptSentiment
|
431 |
+
- 430 promptNLI
|
432 |
+
- 431 promptSpoke
|
433 |
+
- 432 promptProficiency
|
434 |
+
- 433 promptGrammar
|
435 |
+
- 434 promptCoherence
|
436 |
+
- 435 phrase_similarity
|
437 |
+
- 436 scientific-exaggeration-detection
|
438 |
+
- 437 quarel
|
439 |
+
- 438 fever-evidence-related/mwong--fever-related
|
440 |
+
- 439 numer_sense
|
441 |
+
- 440 dynasent/dynabench.dynasent.r1.all/r1
|
442 |
+
- 441 dynasent/dynabench.dynasent.r2.all/r2
|
443 |
+
- 442 Sarcasm_News_Headline
|
444 |
+
- 443 sem_eval_2010_task_8
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"eos_token": "[SEP]",
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"name_or_path": "microsoft/deberta-v3-base",
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"sp_model_kwargs": {},
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"split_by_punct": false,
|
14 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
15 |
+
"unk_token": "[UNK]",
|
16 |
+
"vocab_type": "spm"
|
17 |
+
}
|