{"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":"/paper/distilbert-a-distilled-version-of-bert","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","arxiv_id":"1910.01108","date":"2019-10-02","proceeding":"NeurIPS 2019 12","authors":["Victor Sanh","Lysandre Debut","Julien Chaumond","Thomas Wolf"],"abstract":"As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inference budgets remains challenging. In this work, we propose a method to pre-train a smaller general-purpose language representation model, called DistilBERT, which can then be fine-tuned with good performances on a wide range of tasks like its larger counterparts. While most prior work investigated the use of distillation for building task-specific models, we leverage knowledge distillation during the pre-training phase and show that it is possible to reduce the size of a BERT model by 40%, while retaining 97% of its language understanding capabilities and being 60% faster. To leverage the inductive biases learned by larger models during pre-training, we introduce a triple loss combining language modeling, distillation and cosine-distance losses. Our smaller, faster and lighter model is cheaper to pre-train and we demonstrate its capabilities for on-device computations in a proof-of-concept experiment and a comparative on-device study.","url_abs":"https://arxiv.org/abs/1910.01108v4","url_pdf":"https://arxiv.org/pdf/1910.01108v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/huggingface/swift-coreml-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/huggingface/transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/Milan-Chicago/GLG-Automated-Meta-data-Tagging","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/allenai/scifact","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/askaydevs/distillbert-qa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/ayeffkay/rubert-tiny","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/dngback/co-forget-protocol","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/enzomuschik/distilfnd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/epfml/collaborative-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/facebookresearch/EgoTV","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/flexible-fl/flex-nlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/frankaging/Causal-Distill","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/franknb/Text-Summarization","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/huggingface/node-question-answering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/huggingface/tflite-android-transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/jaketae/pytorch-malware-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/knuddj1/op_text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/knuddy/op_text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/lukexyz/Deep-Lyrical-Genius","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/mkavim/finetune_bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/monologg/distilkobert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/msorkhpar/wiki-entity-summarization-preprocessor","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"CC-BY-4.0"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/nageshsinghc4/deepwrap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/philschmid/knowledge-distillation-transformers-pytorch-sagemaker","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/reycn/multi-modal-scale","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/rybread1/stack-overflow-question-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/sdadas/polish-roberta","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/semantic-web-company/ptlm_wsid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/stefan-it/europeana-bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/suinleelab/path_explain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/tchebonenko/Automated-Topic_Modeling-and-NER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/twobooks/intro-aws-training","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/distilbert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/MindCode-4/code-3/tree/main/distilbert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/MindSpore-paper-code-2/code399/tree/main/Bert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"distilbert-a-distilled-version-of-bert","repo_url":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/distilbert/modeling.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"hate-speech-detection","task_name":"Hate Speech Detection"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"linguistic-acceptability","task_name":"Linguistic Acceptability"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"task-1-grouping","task_name":"Only Connect Walls Dataset Task 1 (Grouping)"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"distilbert","method_name":"DistilBERT"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/linguistic-acceptability-on-cola","task":"Linguistic Acceptability","dataset":"CoLA","model":"DistilBERT 66M","rank_in_archive_order":38,"of":43,"metrics":{"Accuracy":"49.1%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-qnli","task":"Natural Language Inference","dataset":"QNLI","model":"DistilBERT 66M","rank_in_archive_order":36,"of":43,"metrics":{"Accuracy":"90.2%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-rte","task":"Natural Language Inference","dataset":"RTE","model":"DistilBERT 66M","rank_in_archive_order":68,"of":90,"metrics":{"Accuracy":"62.9%"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-inference-on-wnli","task":"Natural Language Inference","dataset":"WNLI","model":"DistilBERT 66M","rank_in_archive_order":23,"of":23,"metrics":{"Accuracy":"44.4"},"uses_additional_data":false},{"leaderboard":"/sota/task-1-grouping-on-ocw","task":"Only Connect Walls Dataset Task 1 (Grouping)","dataset":"OCW","model":"DistilBERT (BASE)","rank_in_archive_order":21,"of":22,"metrics":{"# Correct Groups":"49 ± 4","# Solved Walls":"0 ± 0","Adjusted Mutual Information (AMI)":" 14.0 ± .3","Adjusted Rand Index (ARI)":"11.3 ± .3","Fowlkes Mallows Score (FMS)":"29.1 ± .2","Wasserstein Distance (WD)":"86.7 ± .6"},"uses_additional_data":true},{"leaderboard":"/sota/question-answering-on-multitq","task":"Question Answering","dataset":"MultiTQ","model":"DistillBERT","rank_in_archive_order":10,"of":11,"metrics":{"Hits@1":"8.3","Hits@10":"48.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-quora-question-pairs","task":"Question Answering","dataset":"Quora Question Pairs","model":"DistilBERT 66M","rank_in_archive_order":14,"of":19,"metrics":{"Accuracy":"89.2%"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"DistilBERT","rank_in_archive_order":20,"of":55,"metrics":{"EM":"77.7"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"DistilBERT 66M","rank_in_archive_order":54,"of":55,"metrics":{"F1":"85.8"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-mrpc","task":"Semantic Textual Similarity","dataset":"MRPC","model":"DistilBERT 66M","rank_in_archive_order":14,"of":45,"metrics":{"Accuracy":"90.2%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-textual-similarity-on-sts-benchmark","task":"Semantic Textual Similarity","dataset":"STS Benchmark","model":"DistilBERT 66M","rank_in_archive_order":16,"of":66,"metrics":{"Pearson Correlation":"0.907"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-imdb","task":"Sentiment Analysis","dataset":"IMDb","model":"DistilBERT 66M","rank_in_archive_order":30,"of":49,"metrics":{"Accuracy":"92.82"},"uses_additional_data":false},{"leaderboard":"/sota/sentiment-analysis-on-sst-2-binary","task":"Sentiment Analysis","dataset":"SST-2 Binary classification","model":"DistilBERT 66M","rank_in_archive_order":55,"of":87,"metrics":{"Accuracy":"91.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.01108","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.01108"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/philschmid/knowledge-distillation-transformers-pytorch-sagemaker","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stefan-it/europeana-bert","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Karthik-Bhaskar/Context-Based-Question-Answering","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/msorkhpar/wiki-entity-summarization-preprocessor","reach":{"status":"ok","spdx":"CC-BY-4.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/reycn/multi-modal-scale","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-paper-code-2/code399/tree/main/Bert","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/knuddj1/op_text","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flexible-fl/flex-nlp","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/askaydevs/distillbert-qa","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Milan-Chicago/GLG-Automated-Meta-data-Tagging","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dngback/co-forget-protocol","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleNLP/blob/develop/paddlenlp/transformers/distilbert/modeling.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaketae/pytorch-malware-detection","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lukexyz/Deep-Lyrical-Genius","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/knuddy/op_text","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sdadas/polish-roberta","reach":{"status":"ok","spdx":"LGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tchebonenko/Automated-Topic_Modeling-and-NER","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/monologg/distilkobert","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/distilbert","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-3/tree/main/distilbert","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/EgoTV","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/tflite-android-transformers","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/frankaging/Causal-Distill","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huggingface/node-question-answering","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":7,"ran_fixture":3,"ran_draft_wrong":5,"ran_honours":3,"ran_violates":1,"unverified":8},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":26,"ran":19,"repositories":5}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bd41263948c9f93a","entry":"ArgsAdapterDistilBERT","repo":"epfml/collaborative-attention","repo_kind":"listed","path":"src/collaborative_attention/adapter_distilbert.py","file_url":"https://github.com/epfml/collaborative-attention/blob/HEAD/src/collaborative_attention/adapter_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd41263948c9f93a"}},{"code_sha256_prefix":"d3e9e3aeb78c5878","entry":"DistillBertConfig","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d3e9e3aeb78c5878"}},{"code_sha256_prefix":"c73b35f8741d5bbc","entry":"DistillBertMultiHeadSelfAttention","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c73b35f8741d5bbc"}},{"code_sha256_prefix":"586463f8edb14bc7","entry":"FeedForward","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"586463f8edb14bc7"}},{"code_sha256_prefix":"c01d1e6d469d9bfd","entry":"GroupedBatchSampler","repo":"monologg/distilkobert","repo_kind":"listed","path":"distillation/distiller.py","file_url":"https://github.com/monologg/distilkobert/blob/HEAD/distillation/distiller.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c01d1e6d469d9bfd"}},{"code_sha256_prefix":"aa85de675f71b596","entry":"PretrainedConfig","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa85de675f71b596"}},{"code_sha256_prefix":"f5d6d16633127806","entry":"_quantize","repo":"monologg/distilkobert","repo_kind":"listed","path":"distillation/distiller.py","file_url":"https://github.com/monologg/distilkobert/blob/HEAD/distillation/distiller.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f5d6d16633127806"}},{"code_sha256_prefix":"57e95166ade5f25c","entry":"build_transform","repo":"reycn/multi-modal-scale","repo_kind":"listed","path":"script/3.evaluation.batch.py","file_url":"https://github.com/reycn/multi-modal-scale/blob/HEAD/script/3.evaluation.batch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"57e95166ade5f25c"}},{"code_sha256_prefix":"2fe0a0a44bca4abd","entry":"create_lengths_groups","repo":"monologg/distilkobert","repo_kind":"listed","path":"distillation/distiller.py","file_url":"https://github.com/monologg/distilkobert/blob/HEAD/distillation/distiller.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2fe0a0a44bca4abd"}},{"code_sha256_prefix":"4e8314bcf966eece","entry":"create_position_ids","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4e8314bcf966eece"}},{"code_sha256_prefix":"024e22b6643186b4","entry":"distilbert_layers","repo":"epfml/collaborative-attention","repo_kind":"listed","path":"src/collaborative_attention/adapter_distilbert.py","file_url":"https://github.com/epfml/collaborative-attention/blob/HEAD/src/collaborative_attention/adapter_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"024e22b6643186b4"}},{"code_sha256_prefix":"6dc77bb22fb9d660","entry":"dynamic_preprocess","repo":"reycn/multi-modal-scale","repo_kind":"listed","path":"script/3.evaluation.batch.py","file_url":"https://github.com/reycn/multi-modal-scale/blob/HEAD/script/3.evaluation.batch.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6dc77bb22fb9d660"}},{"code_sha256_prefix":"bd77f5f8067f18e9","entry":"find_closest_aspect_ratio","repo":"reycn/multi-modal-scale","repo_kind":"listed","path":"script/3.evaluation.batch.py","file_url":"https://github.com/reycn/multi-modal-scale/blob/HEAD/script/3.evaluation.batch.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd77f5f8067f18e9"}},{"code_sha256_prefix":"9bc31d06256e1691","entry":"gelu","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9bc31d06256e1691"}},{"code_sha256_prefix":"5b3fd00218623502","entry":"gelu_new","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5b3fd00218623502"}},{"code_sha256_prefix":"333abb7d28cd1f9f","entry":"get_initializer","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"333abb7d28cd1f9f"}},{"code_sha256_prefix":"57e9478bd6df4915","entry":"get_input_mask","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"57e9478bd6df4915"}},{"code_sha256_prefix":"6220c13c591c68a7","entry":"shape_list","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6220c13c591c68a7"}},{"code_sha256_prefix":"86d13b9f67274f19","entry":"swish","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86d13b9f67274f19"}},{"code_sha256_prefix":"299d28a1eb667c41","entry":"DistilBERTCollaborativeAdapter","repo":"epfml/collaborative-attention","repo_kind":"listed","path":"src/collaborative_attention/adapter_distilbert.py","file_url":"https://github.com/epfml/collaborative-attention/blob/HEAD/src/collaborative_attention/adapter_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"299d28a1eb667c41"}},{"code_sha256_prefix":"1f3a00e205369e86","entry":"DistillBertModel","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f3a00e205369e86"}},{"code_sha256_prefix":"604d8efbff65993f","entry":"DistillBertPretrained","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"604d8efbff65993f"}},{"code_sha256_prefix":"20e3c004457d9336","entry":"Distiller","repo":"monologg/distilkobert","repo_kind":"listed","path":"distillation/distiller.py","file_url":"https://github.com/monologg/distilkobert/blob/HEAD/distillation/distiller.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20e3c004457d9336"}},{"code_sha256_prefix":"2efdc2800d06d37c","entry":"LmSeqsDataset","repo":"monologg/distilkobert","repo_kind":"listed","path":"distillation/distiller.py","file_url":"https://github.com/monologg/distilkobert/blob/HEAD/distillation/distiller.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2efdc2800d06d37c"}},{"code_sha256_prefix":"b07754f6f7d44e9e","entry":"get_confidence_scores","repo":"knuddj1/op_text","repo_kind":"listed","path":"op_text/utils.py","file_url":"https://github.com/knuddj1/op_text/blob/HEAD/op_text/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b07754f6f7d44e9e"}},{"code_sha256_prefix":"4db4878c2df8732e","entry":"load_distillbert_model_weights_from_checkpoint","repo":"mkavim/finetune_bert","repo_kind":"listed","path":"finetune/modeling_distilbert.py","file_url":"https://github.com/mkavim/finetune_bert/blob/HEAD/finetune/modeling_distilbert.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4db4878c2df8732e"}},{"code_sha256_prefix":"3ae355fe5a2be50f","entry":"timeit_and_report_mean","repo":"huggingface/swift-coreml-transformers","repo_kind":"official","path":"model_generation/distilbert-onnx-coreml.py","file_url":"https://github.com/huggingface/swift-coreml-transformers/blob/HEAD/model_generation/distilbert-onnx-coreml.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ae355fe5a2be50f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}