{"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/nuteprune-efficient-progressive-pruning-with","title":"NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models","arxiv_id":"2402.09773","date":"2024-02-15","proceeding":null,"authors":["Shengrui Li","Junzhe Chen","Xueting Han","Jing Bai"],"abstract":"The considerable size of Large Language Models (LLMs) presents notable deployment challenges, particularly on resource-constrained hardware. Structured pruning, offers an effective means to compress LLMs, thereby reducing storage costs and enhancing inference speed for more efficient utilization. In this work, we study data-efficient and resource-efficient structure pruning methods to obtain smaller yet still powerful models. Knowledge Distillation is well-suited for pruning, as the intact model can serve as an excellent teacher for pruned students. However, it becomes challenging in the context of LLMs due to memory constraints. To address this, we propose an efficient progressive Numerous-teacher pruning method (NutePrune). NutePrune mitigates excessive memory costs by loading only one intact model and integrating it with various masks and LoRA modules, enabling it to seamlessly switch between teacher and student roles. This approach allows us to leverage numerous teachers with varying capacities to progressively guide the pruned model, enhancing overall performance. Extensive experiments across various tasks demonstrate the effectiveness of NutePrune. In LLaMA-7B zero-shot experiments, NutePrune retains 97.17% of the performance of the original model at 20% sparsity and 95.07% at 25% sparsity. Our code is available at https://github.com/Lucius-lsr/NutePrune.","url_abs":"https://arxiv.org/abs/2402.09773v2","url_pdf":"https://arxiv.org/pdf/2402.09773v2.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":"nuteprune-efficient-progressive-pruning-with","repo_url":"https://github.com/lucius-lsr/nuteprune","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.09773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09773"}},"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/lucius-lsr/nuteprune","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":2,"ran":5,"unverified":7},"by_repo_kind":{"official":{"samples":16,"ran":9,"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":16,"samples":[{"code_sha256_prefix":"30d7eec482ebf6b1","entry":"repeat_kv","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"models/modeling_llama.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/models/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"30d7eec482ebf6b1"}},{"code_sha256_prefix":"d61c483a3c2b3156","entry":"apply_rotary_pos_emb","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"models/modelling_mistral.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/models/modelling_mistral.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d61c483a3c2b3156"}},{"code_sha256_prefix":"d07d04439cd1d44f","entry":"jload","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"tasks/alpaca.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/tasks/alpaca.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":"d07d04439cd1d44f"}},{"code_sha256_prefix":"662f0f3416b6f17e","entry":"process_data","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"eval_ppl.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/eval_ppl.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":"662f0f3416b6f17e"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"models/modelling_mistral.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/models/modelling_mistral.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"a69dcb0d52e1bae2","entry":"set_lora_args","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"merge_weights.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/merge_weights.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":"a69dcb0d52e1bae2"}},{"code_sha256_prefix":"d1da1c0d45d1e6e4","entry":"should_apply_checkpointing_given_lora_config","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"models/modeling_llama.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/models/modeling_llama.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":"d1da1c0d45d1e6e4"}},{"code_sha256_prefix":"dd24b11c0d315807","entry":"should_apply_lora","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"models/modeling_llama.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/models/modeling_llama.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":"dd24b11c0d315807"}},{"code_sha256_prefix":"8528eb0222d2172f","entry":"should_apply_lora","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"models/modelling_opt.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/models/modelling_opt.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":"8528eb0222d2172f"}},{"code_sha256_prefix":"6ada2617ee1d6042","entry":"get_ptb","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"eval_ppl.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/eval_ppl.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":"6ada2617ee1d6042"}},{"code_sha256_prefix":"c31f45d1c5adf4cc","entry":"get_wikitext2","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"eval_ppl.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/eval_ppl.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":"c31f45d1c5adf4cc"}},{"code_sha256_prefix":"d4006675fd1ae88c","entry":"load_l0_module","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"utils/nuteprune_utils.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/utils/nuteprune_utils.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":"d4006675fd1ae88c"}},{"code_sha256_prefix":"9c47a629adf4a03d","entry":"load_model","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"utils/nuteprune_utils.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/utils/nuteprune_utils.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":"9c47a629adf4a03d"}},{"code_sha256_prefix":"14b33fae5b868921","entry":"load_model_with_zs","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"utils/nuteprune_utils.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/utils/nuteprune_utils.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":"14b33fae5b868921"}},{"code_sha256_prefix":"fb1bfd591bf0af2f","entry":"make_supervised_data_module","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"tasks/alpaca.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/tasks/alpaca.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":"fb1bfd591bf0af2f"}},{"code_sha256_prefix":"f6654c046a39662a","entry":"preprocess","repo":"lucius-lsr/nuteprune","repo_kind":"official","path":"tasks/alpaca.py","file_url":"https://github.com/lucius-lsr/nuteprune/blob/HEAD/tasks/alpaca.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":"f6654c046a39662a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}