{"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/structured-pruning-of-large-language-models","title":"Structured Pruning of Large Language Models","arxiv_id":"1910.04732","date":"2019-10-10","proceeding":"EMNLP 2020 11","authors":["Ziheng Wang","Jeremy Wohlwend","Tao Lei"],"abstract":"Large language models have recently achieved state of the art performance across a wide variety of natural language tasks. Meanwhile, the size of these models and their latency have significantly increased, which makes their usage costly, and raises an interesting question: do language models need to be large? We study this question through the lens of model compression. We present a generic, structured pruning approach by parameterizing each weight matrix using its low-rank factorization, and adaptively removing rank-1 components during training. On language modeling tasks, our structured approach outperforms other unstructured and block-structured pruning baselines at various compression levels, while achieving significant speedups during both training and inference. We also demonstrate that our method can be applied to pruning adaptive word embeddings in large language models, and to pruning the BERT model on several downstream fine-tuning classification benchmarks.","url_abs":"https://arxiv.org/abs/1910.04732v2","url_pdf":"https://arxiv.org/pdf/1910.04732v2.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":"structured-pruning-of-large-language-models","repo_url":"https://github.com/asappresearch/flop","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"structured-pruning-of-large-language-models","repo_url":"https://github.com/Holldean/BERT-Pruning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"model-compression","task_name":"Model Compression"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"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":"dropout","method_name":"Dropout"},{"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":"pruning","method_name":"Pruning"},{"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.04732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04732"}},"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/Holldean/BERT-Pruning","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asappresearch/flop","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":9},"by_repo_kind":{"listed":{"samples":12,"ran":3,"repositories":1}},"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":"1923fc05163d207d","entry":"convert_to_unicode","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/tokenization.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/tokenization.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1923fc05163d207d"}},{"code_sha256_prefix":"d08f324f950148de","entry":"gelu","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/modeling.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/modeling.py","link_basis":"harvester_set","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":"d08f324f950148de"}},{"code_sha256_prefix":"5842ee67106321d6","entry":"get_activation","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/modeling.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/modeling.py","link_basis":"harvester_set","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":"5842ee67106321d6"}},{"code_sha256_prefix":"b24b3b9c700da839","entry":"create_float_feature","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/create_pretraining_data.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/create_pretraining_data.py","link_basis":"harvester_set","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":"b24b3b9c700da839"}},{"code_sha256_prefix":"dd3ef48a15aec0cd","entry":"create_int_feature","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/create_pretraining_data.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/create_pretraining_data.py","link_basis":"harvester_set","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":"dd3ef48a15aec0cd"}},{"code_sha256_prefix":"2ffa5353979cd872","entry":"file_based_input_fn_builder","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/run_classifier.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/run_classifier.py","link_basis":"harvester_set","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":"2ffa5353979cd872"}},{"code_sha256_prefix":"50958618b65e514e","entry":"get_assignment_map_from_checkpoint","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/modeling.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/modeling.py","link_basis":"harvester_set","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":"50958618b65e514e"}},{"code_sha256_prefix":"f8b4becf356b99c0","entry":"hard_concrete_mean","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"flop/common.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/flop/common.py","link_basis":"harvester_set","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":"f8b4becf356b99c0"}},{"code_sha256_prefix":"b07e12c3de1d9f3e","entry":"hard_concrete_sample","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"flop/common.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/flop/common.py","link_basis":"harvester_set","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":"b07e12c3de1d9f3e"}},{"code_sha256_prefix":"47a3c792cebb6603","entry":"input_fn_builder","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/extract_features.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/extract_features.py","link_basis":"harvester_set","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":"47a3c792cebb6603"}},{"code_sha256_prefix":"ff83ccc8b0b6462d","entry":"load_vocab","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/tokenization.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/tokenization.py","link_basis":"harvester_set","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":"ff83ccc8b0b6462d"}},{"code_sha256_prefix":"0e5615f8994003cf","entry":"printable_text","repo":"Holldean/BERT-Pruning","repo_kind":"listed","path":"bert/tokenization.py","file_url":"https://github.com/Holldean/BERT-Pruning/blob/HEAD/bert/tokenization.py","link_basis":"harvester_set","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":"0e5615f8994003cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}