{"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/bertmodel","entry":"BertModel","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":16,"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":69,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":69,"n_places_pointer_only":19,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":69},"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":"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":"f90d502733dc3fc8","mcp_get_code":{"code_sha256":"f90d502733dc3fc8"}},{"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":"45e31ada063af6a3","mcp_get_code":{"code_sha256":"45e31ada063af6a3"}},{"arxiv_id":"2210.15332","paper":"/paper/dial2vec-self-guided-contrastive-learning-of","title":"Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings","date":"2022-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AlibabaResearch/DAMO-ConvAI","path":"dial2vec/modeling_bert.py","file_url":"https://github.com/AlibabaResearch/DAMO-ConvAI/blob/HEAD/dial2vec/modeling_bert.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7725d578d6fc49c","mcp_get_code":{"code_sha256":"a7725d578d6fc49c"}},{"arxiv_id":"2203.03825","paper":"/paper/incorporating-hierarchy-into-text-encoder-a","title":"Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification","date":"2022-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wzh9969/contrastive-htc","path":"model/contrast.py","file_url":"https://github.com/wzh9969/contrastive-htc/blob/HEAD/model/contrast.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1b18fd412b5eaf7b","mcp_get_code":{"code_sha256":"1b18fd412b5eaf7b"}},{"arxiv_id":"2104.08821","paper":"/paper/simcse-simple-contrastive-learning-of","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","date":"2021-04-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jeongukjae/KR-BERT-SimCSE","path":"model.py","file_url":"https://github.com/jeongukjae/KR-BERT-SimCSE/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1d4fef90a4837857","mcp_get_code":{"code_sha256":"1d4fef90a4837857"}},{"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":"f31e6bafe1bf135f","mcp_get_code":{"code_sha256":"f31e6bafe1bf135f"}},{"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":"cea3c58496f17080","mcp_get_code":{"code_sha256":"cea3c58496f17080"}},{"arxiv_id":"2009.07602","paper":"/paper/union-an-unreferenced-metric-for-evaluating","title":"UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation","date":"2020-09-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/UNION","path":"union_modeling.py","file_url":"https://github.com/thu-coai/UNION/blob/HEAD/union_modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ce3b439893c9fa27","mcp_get_code":{"code_sha256":"ce3b439893c9fa27"}},{"arxiv_id":"2009.07258","paper":"/paper/bert-qe-contextualized-query-expansion-for","title":"BERT-QE: Contextualized Query Expansion for Document Re-ranking","date":"2020-09-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zh-zheng/BERT-QE","path":"functions.py","file_url":"https://github.com/zh-zheng/BERT-QE/blob/HEAD/functions.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":"d1820cb4dd9e6cb4","mcp_get_code":{"code_sha256":"d1820cb4dd9e6cb4"}},{"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":"b76586b7d7a5e61f","mcp_get_code":{"code_sha256":"b76586b7d7a5e61f"}},{"arxiv_id":"2004.11579","paper":"/paper/probabilistically-masked-language-model","title":"Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order","date":"2020-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/Pretrained-Language-Model","path":"PMLM/interactive_conditional_samples_sincos_acrostic.py","file_url":"https://github.com/huawei-noah/Pretrained-Language-Model/blob/HEAD/PMLM/interactive_conditional_samples_sincos_acrostic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3c86b7d1ed73e184","mcp_get_code":{"code_sha256":"3c86b7d1ed73e184"}},{"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":"ee054708d97537c8","mcp_get_code":{"code_sha256":"ee054708d97537c8"}},{"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":"f43b4161b7bdba24","mcp_get_code":{"code_sha256":"f43b4161b7bdba24"}},{"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":"d94fb1043848be78","mcp_get_code":{"code_sha256":"d94fb1043848be78"}},{"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":"TeamLab/bert-gcn-for-paper-citation","path":"modeling.py","file_url":"https://github.com/TeamLab/bert-gcn-for-paper-citation/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":"c1c5de65dfedcf88","mcp_get_code":{"code_sha256":"c1c5de65dfedcf88"}},{"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":"DeligientSloth/bert-tensorflow","path":"modeling.py","file_url":"https://github.com/DeligientSloth/bert-tensorflow/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":"b84a7e54141c42d4","mcp_get_code":{"code_sha256":"b84a7e54141c42d4"}},{"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":"wchh127/yykf","path":"modeling.py","file_url":"https://github.com/wchh127/yykf/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":"f298a22a9d079be3","mcp_get_code":{"code_sha256":"f298a22a9d079be3"}},{"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":"57ddc6f7b4914314","mcp_get_code":{"code_sha256":"57ddc6f7b4914314"}},{"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":"0a619d4800774912","mcp_get_code":{"code_sha256":"0a619d4800774912"}},{"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":"Satan012/BERT","path":"modeling.py","file_url":"https://github.com/Satan012/BERT/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":"1c8f5d63388f5841","mcp_get_code":{"code_sha256":"1c8f5d63388f5841"}},{"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":"h4ste/oscar","path":"modeling.py","file_url":"https://github.com/h4ste/oscar/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":"4d900dd3364ebe60","mcp_get_code":{"code_sha256":"4d900dd3364ebe60"}},{"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":"chiayewken/bert-qa","path":"modeling.py","file_url":"https://github.com/chiayewken/bert-qa/blob/HEAD/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"73c88a124156227a","mcp_get_code":{"code_sha256":"73c88a124156227a"}},{"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":"DeligientSloth/QQsim","path":"modeling.py","file_url":"https://github.com/DeligientSloth/QQsim/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":"f7810bd4cfcb3f72","mcp_get_code":{"code_sha256":"f7810bd4cfcb3f72"}},{"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":"brightmart/text_classification","path":"a00_Bert/bert_modeling.py","file_url":"https://github.com/brightmart/text_classification/blob/HEAD/a00_Bert/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":"d550d4124042659c","mcp_get_code":{"code_sha256":"d550d4124042659c"}},{"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":"StuartCHAN/KARL","path":"bert/modeling.py","file_url":"https://github.com/StuartCHAN/KARL/blob/HEAD/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":"6f4396a03cbaf31e","mcp_get_code":{"code_sha256":"6f4396a03cbaf31e"}},{"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":"frankcgq105/BERTCHEN","path":"modeling.py","file_url":"https://github.com/frankcgq105/BERTCHEN/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":"0ee385ced53dea5b","mcp_get_code":{"code_sha256":"0ee385ced53dea5b"}},{"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":"Nstats/bert_MRC","path":"modeling.py","file_url":"https://github.com/Nstats/bert_MRC/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":"730874f4bd9c228f","mcp_get_code":{"code_sha256":"730874f4bd9c228f"}},{"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":"7fcd355aa43ef519","mcp_get_code":{"code_sha256":"7fcd355aa43ef519"}},{"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":"google-research/bigbird","path":"bigbird/core/modeling.py","file_url":"https://github.com/google-research/bigbird/blob/HEAD/bigbird/core/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":"3625fdaae4382d86","mcp_get_code":{"code_sha256":"3625fdaae4382d86"}},{"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":"socc-io/piqaboo","path":"modeling.py","file_url":"https://github.com/socc-io/piqaboo/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":"5edefb59760db592","mcp_get_code":{"code_sha256":"5edefb59760db592"}},{"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":"mkavim/finetune_bert","path":"finetune/modeling_bert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_bert.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":"4ad0a0a5c8931d4f","mcp_get_code":{"code_sha256":"4ad0a0a5c8931d4f"}},{"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":"c499a33e67b2478d","mcp_get_code":{"code_sha256":"c499a33e67b2478d"}},{"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":"guoyaohua/BERT-Classifier","path":"modeling.py","file_url":"https://github.com/guoyaohua/BERT-Classifier/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":"a3b61b2a031736be","mcp_get_code":{"code_sha256":"a3b61b2a031736be"}},{"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":"pengshuyuan/Bert","path":"modeling.py","file_url":"https://github.com/pengshuyuan/Bert/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":"a05a5798905d6dd0","mcp_get_code":{"code_sha256":"a05a5798905d6dd0"}},{"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":"dc676111545d7cd3","mcp_get_code":{"code_sha256":"dc676111545d7cd3"}},{"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":"1cf3945c98c6c2f3","mcp_get_code":{"code_sha256":"1cf3945c98c6c2f3"}},{"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":"meelfy/pytorch_pretrained_bert","path":"pytorch_pretrained_bert/modeling.py","file_url":"https://github.com/meelfy/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":"6725fc5eaa566426","mcp_get_code":{"code_sha256":"6725fc5eaa566426"}},{"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":"SYangDong/bert-with-frozen-code","path":"modeling.py","file_url":"https://github.com/SYangDong/bert-with-frozen-code/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":"03e35473217340bd","mcp_get_code":{"code_sha256":"03e35473217340bd"}},{"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":"zsweet/BERT_zsw","path":"modeling.py","file_url":"https://github.com/zsweet/BERT_zsw/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":"9bf7e74f61786136","mcp_get_code":{"code_sha256":"9bf7e74f61786136"}},{"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":"algharak/BERTenhance","path":"modeling.py","file_url":"https://github.com/algharak/BERTenhance/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":"7e08ad549a7e13fb","mcp_get_code":{"code_sha256":"7e08ad549a7e13fb"}},{"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":"59bcd923687ae5b0","mcp_get_code":{"code_sha256":"59bcd923687ae5b0"}},{"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":"KnightZhang625/BERT_TF","path":"model_official.py","file_url":"https://github.com/KnightZhang625/BERT_TF/blob/HEAD/model_official.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":"6d2298e39819682c","mcp_get_code":{"code_sha256":"6d2298e39819682c"}},{"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":"teghub/TurkishNER-BERT","path":"bert/modeling.py","file_url":"https://github.com/teghub/TurkishNER-BERT/blob/HEAD/bert/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e9ff615e1693ffe4","mcp_get_code":{"code_sha256":"e9ff615e1693ffe4"}},{"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":"7014de3eb8095b4c","mcp_get_code":{"code_sha256":"7014de3eb8095b4c"}},{"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":"Nstats/my_bert","path":"modeling.py","file_url":"https://github.com/Nstats/my_bert/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":"18d72628a65b6b75","mcp_get_code":{"code_sha256":"18d72628a65b6b75"}},{"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":"b012d23ee83351a2","mcp_get_code":{"code_sha256":"b012d23ee83351a2"}},{"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":"deepmipt/bert","path":"bert_dp/modeling.py","file_url":"https://github.com/deepmipt/bert/blob/HEAD/bert_dp/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":"558426bb4445df9f","mcp_get_code":{"code_sha256":"558426bb4445df9f"}},{"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":"jageshmaharjan/BERT_Service","path":"bert/modeling.py","file_url":"https://github.com/jageshmaharjan/BERT_Service/blob/HEAD/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":"59d9d9684a5da4c8","mcp_get_code":{"code_sha256":"59d9d9684a5da4c8"}},{"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":"haidershaour/bert","path":"modeling.py","file_url":"https://github.com/haidershaour/bert/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":"8817d532f8aedb47","mcp_get_code":{"code_sha256":"8817d532f8aedb47"}},{"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":"semal/bert","path":"bert/core/modeling.py","file_url":"https://github.com/semal/bert/blob/HEAD/bert/core/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":"5eb87d3a8fc7de9a","mcp_get_code":{"code_sha256":"5eb87d3a8fc7de9a"}},{"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":"SCismycat/bert_code_view","path":"modeling.py","file_url":"https://github.com/SCismycat/bert_code_view/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":"ecfe55dea456ed37","mcp_get_code":{"code_sha256":"ecfe55dea456ed37"}},{"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":"JNUpython/bert","path":"bert_base/modeling.py","file_url":"https://github.com/JNUpython/bert/blob/HEAD/bert_base/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d48289b49ea0e641","mcp_get_code":{"code_sha256":"d48289b49ea0e641"}},{"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":"SkullFang/BERT_NLP_Classification","path":"modeling.py","file_url":"https://github.com/SkullFang/BERT_NLP_Classification/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":"ef1cb1634a1b5c69","mcp_get_code":{"code_sha256":"ef1cb1634a1b5c69"}},{"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":"ricardordb/bert","path":"modeling.py","file_url":"https://github.com/ricardordb/bert/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":"cdeaf8a002ca4b94","mcp_get_code":{"code_sha256":"cdeaf8a002ca4b94"}},{"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":"yydai/bert_test","path":"modeling.py","file_url":"https://github.com/yydai/bert_test/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":"0326eaf7306ca80c","mcp_get_code":{"code_sha256":"0326eaf7306ca80c"}},{"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":"MichaelZhouwang/LMlexsub","path":"modeling.py","file_url":"https://github.com/MichaelZhouwang/LMlexsub/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":"3ade46b481d63b92","mcp_get_code":{"code_sha256":"3ade46b481d63b92"}},{"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":"appcoreopc/berty","path":"modeling.py","file_url":"https://github.com/appcoreopc/berty/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":"4cbce5db2a203a79","mcp_get_code":{"code_sha256":"4cbce5db2a203a79"}},{"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":"xiangyue9607/CliniRC","path":"BERT/modeling.py","file_url":"https://github.com/xiangyue9607/CliniRC/blob/HEAD/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":"4b258860805ea4d3","mcp_get_code":{"code_sha256":"4b258860805ea4d3"}},{"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":"benywon/ChineseBert","path":"model.py","file_url":"https://github.com/benywon/ChineseBert/blob/HEAD/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cff5f4809af22623","mcp_get_code":{"code_sha256":"cff5f4809af22623"}},{"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":"a9444eeb146ebd10","mcp_get_code":{"code_sha256":"a9444eeb146ebd10"}},{"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":"tcnguyen/bert","path":"modeling.py","file_url":"https://github.com/tcnguyen/bert/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":"07bff76d62731e8d","mcp_get_code":{"code_sha256":"07bff76d62731e8d"}},{"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":"joongbo/tta","path":"modeling.py","file_url":"https://github.com/joongbo/tta/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":"d62d803ad81a8a4a","mcp_get_code":{"code_sha256":"d62d803ad81a8a4a"}},{"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":"Skumarr53/Attention-is-All-you-Need-PyTorch","path":"transformer/model.py","file_url":"https://github.com/Skumarr53/Attention-is-All-you-Need-PyTorch/blob/HEAD/transformer/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fa0ddb048557dd4a","mcp_get_code":{"code_sha256":"fa0ddb048557dd4a"}},{"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":"goodluck4s/bert-","path":"modeling.py","file_url":"https://github.com/goodluck4s/bert-/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":"1dc5a90b12f37329","mcp_get_code":{"code_sha256":"1dc5a90b12f37329"}},{"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":"goldenbili/Bert_Test2","path":"modeling.py","file_url":"https://github.com/goldenbili/Bert_Test2/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":"eebd62f1e724cbb4","mcp_get_code":{"code_sha256":"eebd62f1e724cbb4"}},{"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":"brightmart/bert_customized","path":"modeling.py","file_url":"https://github.com/brightmart/bert_customized/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":"5e83fb6cbfb3f5a1","mcp_get_code":{"code_sha256":"5e83fb6cbfb3f5a1"}},{"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":"4f399deeb0300ce5","mcp_get_code":{"code_sha256":"4f399deeb0300ce5"}},{"arxiv_id":"2023.acl-long.693","paper":null,"title":"arXiv:2023.acl-long.693","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"AI4Bharat/IndicBERT","path":"train/modeling.py","file_url":"https://github.com/AI4Bharat/IndicBERT/blob/HEAD/train/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad3f6cc29c24cd18","mcp_get_code":{"code_sha256":"ad3f6cc29c24cd18"}},{"arxiv_id":"2021.acl-long.233","paper":null,"title":"arXiv:2021.acl-long.233","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ACL2020SpellGCN/SpellGCN","path":"modeling.py","file_url":"https://github.com/ACL2020SpellGCN/SpellGCN/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":"ef690d1e8fe5cd60","mcp_get_code":{"code_sha256":"ef690d1e8fe5cd60"}}]}