{"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/bertpretrainedmodel","entry":"BertPreTrainedModel","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":7,"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":14,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":14,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":14},"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":"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":"cfb69ead0a67f2fe","mcp_get_code":{"code_sha256":"cfb69ead0a67f2fe"}},{"arxiv_id":"2107.14596","paper":"/paper/multi-stage-pre-training-over-simplified","title":"Multi-stage Pre-training over Simplified Multimodal Pre-training Models","date":"2021-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lttsmn/LXMERT-S","path":"Desktop/LXMERT_S/src/lxrt/modeling.py","file_url":"https://github.com/lttsmn/LXMERT-S/blob/HEAD/Desktop/LXMERT_S/src/lxrt/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"189cb1190e0c5d7f","mcp_get_code":{"code_sha256":"189cb1190e0c5d7f"}},{"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":"fe3c40780a0269fa","mcp_get_code":{"code_sha256":"fe3c40780a0269fa"}},{"arxiv_id":"2101.08106","paper":"/paper/learning-to-augment-for-data-scarce-domain","title":"Learning to Augment for Data-Scarce Domain BERT Knowledge Distillation","date":"2021-01-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huawei-noah/Pretrained-Language-Model","path":"AutoTinyBERT/transformer/modeling_super_kd.py","file_url":"https://github.com/huawei-noah/Pretrained-Language-Model/blob/HEAD/AutoTinyBERT/transformer/modeling_super_kd.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aa473329a2bdbd95","mcp_get_code":{"code_sha256":"aa473329a2bdbd95"}},{"arxiv_id":"1908.07490","paper":"/paper/lxmert-learning-cross-modality-encoder","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","date":"2019-08-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ghazaleh-mahmoodi/lxmert_compression","path":"lxmert/src/lxrt/modeling.py","file_url":"https://github.com/ghazaleh-mahmoodi/lxmert_compression/blob/HEAD/lxmert/src/lxrt/modeling.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"805f9fc004ffa11b","mcp_get_code":{"code_sha256":"805f9fc004ffa11b"}},{"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":"4bd7a207408ee835","mcp_get_code":{"code_sha256":"4bd7a207408ee835"}},{"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":"fdd3d4990bea9d9c","mcp_get_code":{"code_sha256":"fdd3d4990bea9d9c"}},{"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":"39f5d68d67913dc7","mcp_get_code":{"code_sha256":"39f5d68d67913dc7"}},{"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":"a058c7071e411484","mcp_get_code":{"code_sha256":"a058c7071e411484"}},{"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":"8d35a5c30d46d2df","mcp_get_code":{"code_sha256":"8d35a5c30d46d2df"}},{"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":"79c6bbbf312efc13","mcp_get_code":{"code_sha256":"79c6bbbf312efc13"}},{"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":"d3b9deead826313f","mcp_get_code":{"code_sha256":"d3b9deead826313f"}},{"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":"a8dd78eaed472e6c","mcp_get_code":{"code_sha256":"a8dd78eaed472e6c"}},{"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":"894b867bfd628865","mcp_get_code":{"code_sha256":"894b867bfd628865"}}]}