{"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/one-shot-sensitivity-aware-mixed-sparsity","title":"One-Shot Sensitivity-Aware Mixed Sparsity Pruning for Large Language Models","arxiv_id":"2310.09499","date":"2023-10-14","proceeding":null,"authors":["Hang Shao","Bei Liu","Bo Xiao","Ke Zeng","Guanglu Wan","Yanmin Qian"],"abstract":"Various Large Language Models~(LLMs) from the Generative Pretrained Transformer(GPT) family have achieved outstanding performances in a wide range of text generation tasks. However, the enormous model sizes have hindered their practical use in real-world applications due to high inference latency. Therefore, improving the efficiencies of LLMs through quantization, pruning, and other means has been a key issue in LLM studies. In this work, we propose a method based on Hessian sensitivity-aware mixed sparsity pruning to prune LLMs to at least 50% sparsity without the need of any retraining. It allocates sparsity adaptively based on sensitivity, allowing us to reduce pruning-induced error while maintaining the overall sparsity level. The advantages of the proposed method exhibit even more when the sparsity is extremely high. Furthermore, our method is compatible with quantization, enabling further compression of LLMs. We have released the available code.","url_abs":"https://arxiv.org/abs/2310.09499v4","url_pdf":"https://arxiv.org/pdf/2310.09499v4.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":"one-shot-sensitivity-aware-mixed-sparsity","repo_url":"https://github.com/talkking/MixGPT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"sensitivity","task_name":"Sensitivity"},{"task_slug":"text-generation","task_name":"Text Generation"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.09499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.09499"}},"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/talkking/MixGPT","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":11,"ran":4,"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":11,"samples":[{"code_sha256_prefix":"a9e7f2cdf016b88b","entry":"find_layers","repo":"talkking/MixGPT","repo_kind":"official","path":"modelutils.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/modelutils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9e7f2cdf016b88b"}},{"code_sha256_prefix":"cd666c16d4aaa66d","entry":"get_bloom","repo":"talkking/MixGPT","repo_kind":"official","path":"bloom.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/bloom.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cd666c16d4aaa66d"}},{"code_sha256_prefix":"88d590323ed219c8","entry":"get_llama","repo":"talkking/MixGPT","repo_kind":"official","path":"llama.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/llama.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88d590323ed219c8"}},{"code_sha256_prefix":"757e95a1449ceb9d","entry":"to_device","repo":"talkking/MixGPT","repo_kind":"official","path":"modelutils.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/modelutils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"757e95a1449ceb9d"}},{"code_sha256_prefix":"5076786563dd8499","entry":"bloom_sequential","repo":"talkking/MixGPT","repo_kind":"official","path":"bloom.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/bloom.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5076786563dd8499"}},{"code_sha256_prefix":"48824cfebb89d72b","entry":"get_baichuan","repo":"talkking/MixGPT","repo_kind":"official","path":"baichuan.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/baichuan.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48824cfebb89d72b"}},{"code_sha256_prefix":"4d2407d067e143c7","entry":"get_llama2","repo":"talkking/MixGPT","repo_kind":"official","path":"llama2.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/llama2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4d2407d067e143c7"}},{"code_sha256_prefix":"a0f5f02456fb742d","entry":"get_opt","repo":"talkking/MixGPT","repo_kind":"official","path":"opt.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/opt.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a0f5f02456fb742d"}},{"code_sha256_prefix":"7d205a0e647139ae","entry":"get_ptb","repo":"talkking/MixGPT","repo_kind":"official","path":"datautils.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/datautils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7d205a0e647139ae"}},{"code_sha256_prefix":"d3a67ecb7951ec5c","entry":"get_tokenizer","repo":"talkking/MixGPT","repo_kind":"official","path":"datautils.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/datautils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d3a67ecb7951ec5c"}},{"code_sha256_prefix":"cb4c3b607eb16747","entry":"get_wikitext2","repo":"talkking/MixGPT","repo_kind":"official","path":"datautils.py","file_url":"https://github.com/talkking/MixGPT/blob/HEAD/datautils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb4c3b607eb16747"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}