{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/bertencoder","entry":"BertEncoder","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":20,"n_papers_ran":0,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":31,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":31,"n_places_pointer_only":13,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":31},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2501.03835","paper":"/paper/taclr-a-scalable-and-efficient-retrieval","title":"TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification","date":"2025-01-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SuYindu/TACLR","path":"src/model/plm_ret.py","file_url":"https://github.com/SuYindu/TACLR/blob/HEAD/src/model/plm_ret.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dde66aaf0b6da6ae","mcp_get_code":{"code_sha256":"dde66aaf0b6da6ae"}},{"arxiv_id":"2308.12587","paper":"/paper/grounded-entity-landmark-adaptive-pre","title":"Grounded Entity-Landmark Adaptive Pre-training for Vision-and-Language Navigation","date":"2023-08-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csir1996/vln-gela","path":"ada_pretrain_src/model/pretrain_cmt.py","file_url":"https://github.com/csir1996/vln-gela/blob/HEAD/ada_pretrain_src/model/pretrain_cmt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8654eadc64d1d6d9","mcp_get_code":{"code_sha256":"8654eadc64d1d6d9"}},{"arxiv_id":"2306.15006","paper":"/paper/dnabert-2-efficient-foundation-model-and","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","date":"2023-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"frederikkemarin/bend","path":"bend/utils/embedders.py","file_url":"https://github.com/frederikkemarin/bend/blob/HEAD/bend/utils/embedders.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"3386604c83d5235b","mcp_get_code":{"code_sha256":"3386604c83d5235b"}},{"arxiv_id":"2305.12074","paper":"/paper/disco-distilled-student-models-co-training","title":"DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining","date":"2023-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"litesslhub/disco","path":"src/model.py","file_url":"https://github.com/litesslhub/disco/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"35992cbf0288d2de","mcp_get_code":{"code_sha256":"35992cbf0288d2de"}},{"arxiv_id":"2305.03602","paper":"/paper/a-dual-semantic-aware-recurrent-global","title":"A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigation","date":"2023-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"CrystalSixone/DSRG","path":"finetune_src/models/vilmodel.py","file_url":"https://github.com/CrystalSixone/DSRG/blob/HEAD/finetune_src/models/vilmodel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1ae89ecd5c078970","mcp_get_code":{"code_sha256":"1ae89ecd5c078970"}},{"arxiv_id":"2301.13155","paper":"/paper/advancing-radiograph-representation-learning","title":"Advancing Radiograph Representation Learning with Masked Record Modeling","date":"2023-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rl4m/mrm-pytorch","path":"model_mrm.py","file_url":"https://github.com/rl4m/mrm-pytorch/blob/HEAD/model_mrm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"10e6fbb7187a0639","mcp_get_code":{"code_sha256":"10e6fbb7187a0639"}},{"arxiv_id":"2210.08714","paper":"/paper/selective-query-guided-debiasing-network-for","title":"Selective Query-guided Debiasing for Video Corpus Moment Retrieval","date":"2022-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dbstjswo505/SQuiDNet","path":"model/squidnet.py","file_url":"https://github.com/dbstjswo505/SQuiDNet/blob/HEAD/model/squidnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3c05ca4aa7639bb1","mcp_get_code":{"code_sha256":"3c05ca4aa7639bb1"}},{"arxiv_id":"2205.00274","paper":"/paper/clues-before-answers-generation-enhanced","title":"Clues Before Answers: Generation-Enhanced Multiple-Choice QA","date":"2022-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nju-websoft/GenMC","path":"model/modeling_genmc.py","file_url":"https://github.com/nju-websoft/GenMC/blob/HEAD/model/modeling_genmc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f2960095c4691870","mcp_get_code":{"code_sha256":"f2960095c4691870"}},{"arxiv_id":"2203.14040","paper":"/paper/visual-abductive-reasoning","title":"Visual Abductive Reasoning","date":"2022-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leonnnop/var","path":"src/model/mainmodel.py","file_url":"https://github.com/leonnnop/var/blob/HEAD/src/model/mainmodel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2fbca415e4e6bf08","mcp_get_code":{"code_sha256":"2fbca415e4e6bf08"}},{"arxiv_id":"2203.09101","paper":"/paper/relationprompt-leveraging-prompts-to-generate","title":"RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction","date":"2022-03-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"declare-lab/hyperred","path":"modeling.py","file_url":"https://github.com/declare-lab/hyperred/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3af493846de2812","mcp_get_code":{"code_sha256":"e3af493846de2812"}},{"arxiv_id":"2110.13309","paper":"/paper/history-aware-multimodal-transformer-for","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","date":"2021-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cshizhe/vln-hamt","path":"finetune_src/models/vilmodel_cmt.py","file_url":"https://github.com/cshizhe/vln-hamt/blob/HEAD/finetune_src/models/vilmodel_cmt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"35a750d77f3a1303","mcp_get_code":{"code_sha256":"35a750d77f3a1303"}},{"arxiv_id":"2105.03761","paper":"/paper/e-vil-a-dataset-and-benchmark-for-natural","title":"e-ViL: A Dataset and Benchmark for Natural Language Explanations in Vision-Language Tasks","date":"2021-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maximek3/e-ViL","path":"src/modeling.py","file_url":"https://github.com/maximek3/e-ViL/blob/HEAD/src/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"28583b97c6efcaf1","mcp_get_code":{"code_sha256":"28583b97c6efcaf1"}},{"arxiv_id":"2011.05268","paper":"/paper/towards-interpretable-natural-language","title":"Towards Interpretable Natural Language Understanding with Explanations as Latent Variables","date":"2020-10-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JamesHujy/ELV","path":"ELV_re/s2s_ft/modeling_decoding.py","file_url":"https://github.com/JamesHujy/ELV/blob/HEAD/ELV_re/s2s_ft/modeling_decoding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fcc6106b91ccf5a8","mcp_get_code":{"code_sha256":"fcc6106b91ccf5a8"}},{"arxiv_id":"2010.08210","paper":"/paper/coarse-to-fine-pre-training-for-named-entity","title":"Coarse-to-Fine Pre-training for Named Entity Recognition","date":"2020-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"strawberryx/CoFEE","path":"model/bert_mrc_ner_cluster.py","file_url":"https://github.com/strawberryx/CoFEE/blob/HEAD/model/bert_mrc_ner_cluster.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"165467596b516ee3","mcp_get_code":{"code_sha256":"165467596b516ee3"}},{"arxiv_id":"2005.00697","paper":"/paper/deformer-decomposing-pre-trained-transformers","title":"DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering","date":"2020-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"StonyBrookNLP/deformer","path":"models/layers/transformer.py","file_url":"https://github.com/StonyBrookNLP/deformer/blob/HEAD/models/layers/transformer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fe2a344ff9027718","mcp_get_code":{"code_sha256":"fe2a344ff9027718"}},{"arxiv_id":"2004.13278","paper":"/paper/vd-bert-a-unified-vision-and-dialog","title":"VD-BERT: A Unified Vision and Dialog Transformer with BERT","date":"2020-04-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salesforce/VD-BERT","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/salesforce/VD-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3001206d0b79eb22","mcp_get_code":{"code_sha256":"3001206d0b79eb22"}},{"arxiv_id":"1908.03557","paper":"/paper/visualbert-a-simple-and-performant-baseline","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","date":"2019-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YIKUAN8/Transformers-VQA","path":"src/modeling.py","file_url":"https://github.com/YIKUAN8/Transformers-VQA/blob/HEAD/src/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"59f36be33253afad","mcp_get_code":{"code_sha256":"59f36be33253afad"}},{"arxiv_id":"1908.02265","paper":"/paper/vilbert-pretraining-task-agnostic","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","date":"2019-08-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jiasenlu/vilbert_beta","path":"vilbert/vilbert.py","file_url":"https://github.com/jiasenlu/vilbert_beta/blob/HEAD/vilbert/vilbert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e91ad90558db9297","mcp_get_code":{"code_sha256":"e91ad90558db9297"}},{"arxiv_id":"1907.11692","paper":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data","path":"run_hbm.py","file_url":"https://github.com/GeorgeLuImmortal/Hierarchical-BERT-Model-with-Limited-Labelled-Data/blob/HEAD/run_hbm.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"00ea7705507db813","mcp_get_code":{"code_sha256":"00ea7705507db813"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cedrickchee/pytorch-pretrained-BERT","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/cedrickchee/pytorch-pretrained-BERT/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0be65efc892d53b9","mcp_get_code":{"code_sha256":"0be65efc892d53b9"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"derronxu/sparsebert","path":"SparseBERT/main_functions/transformer/modeling.py","file_url":"https://github.com/derronxu/sparsebert/blob/HEAD/SparseBERT/main_functions/transformer/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b824da45c7d85285","mcp_get_code":{"code_sha256":"b824da45c7d85285"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lonePatient/ERNIE-text-classification-pytorch","path":"pyernie/model/ernie/modeling.py","file_url":"https://github.com/lonePatient/ERNIE-text-classification-pytorch/blob/HEAD/pyernie/model/ernie/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"064f9026080680e2","mcp_get_code":{"code_sha256":"064f9026080680e2"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wyf-python/Bert-Pytorch-TextClassification","path":"pytorch_pretrained/modeling.py","file_url":"https://github.com/wyf-python/Bert-Pytorch-TextClassification/blob/HEAD/pytorch_pretrained/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"348c6586dd6fcb82","mcp_get_code":{"code_sha256":"348c6586dd6fcb82"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EuphoriaYan/bert_component","path":"layers/bert_basic_model.py","file_url":"https://github.com/EuphoriaYan/bert_component/blob/HEAD/layers/bert_basic_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7bbb022fe9e684b4","mcp_get_code":{"code_sha256":"7bbb022fe9e684b4"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Impavidity/relogic","path":"relogic/logickit/inference/modeling.py","file_url":"https://github.com/Impavidity/relogic/blob/HEAD/relogic/logickit/inference/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6592c17758687a36","mcp_get_code":{"code_sha256":"6592c17758687a36"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ganeshjawahar/interpret_bert","path":"tpdn/unsuptree_modeler.py","file_url":"https://github.com/ganeshjawahar/interpret_bert/blob/HEAD/tpdn/unsuptree_modeler.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"e23a8af897f865c5","mcp_get_code":{"code_sha256":"e23a8af897f865c5"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifding/hetseq","path":"hetseq/bert_modeling.py","file_url":"https://github.com/yifding/hetseq/blob/HEAD/hetseq/bert_modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"87487781c4dcd1a1","mcp_get_code":{"code_sha256":"87487781c4dcd1a1"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cybertronai/megatron-lm","path":"model/modeling.py","file_url":"https://github.com/cybertronai/megatron-lm/blob/HEAD/model/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"4c39e580d926b422","mcp_get_code":{"code_sha256":"4c39e580d926b422"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"han-shi/SparseBERT","path":"modeling.py","file_url":"https://github.com/han-shi/SparseBERT/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"3b780454a1b795ae","mcp_get_code":{"code_sha256":"3b780454a1b795ae"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"charles9n/bert-sklearn","path":"bert_sklearn/model/pytorch_pretrained/modeling.py","file_url":"https://github.com/charles9n/bert-sklearn/blob/HEAD/bert_sklearn/model/pytorch_pretrained/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"b47ae2a32bd23a1c","mcp_get_code":{"code_sha256":"b47ae2a32bd23a1c"}},{"arxiv_id":"1810.04805","paper":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maknotavailable/pytorch-pretrained-bert","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/maknotavailable/pytorch-pretrained-bert/blob/HEAD/pytorch_pretrained_bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7e1548e1a31a85bc","mcp_get_code":{"code_sha256":"7e1548e1a31a85bc"}}]}