{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/parameter-efficient-sparsity-crafting-from","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","arxiv_id":"2401.02731","date":"2024-01-05","proceeding":null,"authors":["Haoyuan Wu","Haisheng Zheng","Zhuolun He","Bei Yu"],"abstract":"Large language models (LLMs) have demonstrated considerable proficiency in general natural language processing (NLP) tasks. Instruction tuning, a successful paradigm, enhances the ability of LLMs to follow natural language instructions and exhibit robust generalization across general tasks. However, these models often encounter performance limitations across multiple tasks due to constrained model capacity. Expanding this capacity during the instruction tuning phase poses significant challenges. To address this issue, we introduce parameter-efficient sparsity crafting (PESC), which crafts dense models into sparse models using the mixture-of-experts (MoE) architecture. PESC integrates adapters into the MoE layers of sparse models, differentiating experts without altering the individual weights within these layers. This method significantly reduces computational costs and GPU memory requirements, facilitating model capacity expansion through a minimal parameter increase when guaranteeing the quality of approximation in function space compared to original sparse upcycling. Our empirical evaluation demonstrates the effectiveness of the PESC method. Using PESC during instruction tuning, our best sparse model outperforms other sparse and dense models and exhibits superior general capabilities compared to GPT-3.5. Our code is available at https://github.com/wuhy68/Parameter-Efficient-MoE.","url_abs":"https://arxiv.org/abs/2401.02731v4","url_pdf":"https://arxiv.org/pdf/2401.02731v4.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":"parameter-efficient-sparsity-crafting-from","repo_url":"https://github.com/wuhy68/parameter-efficient-moe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"parameter-efficient-sparsity-crafting-from","repo_url":"https://github.com/ShayekhBinIslam/openrag","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"math-word-problem-solving","task_name":"Math Word Problem Solving"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"multi-task-language-understanding","task_name":"Multi-task Language Understanding"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"sentence-completion","task_name":"Sentence Completion"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Camelidae-8×34B (5-shot)","rank_in_archive_order":78,"of":164,"metrics":{"Accuracy":"78.3"},"uses_additional_data":false},{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"Qwen2idae-16x14B (5-shot)","rank_in_archive_order":79,"of":164,"metrics":{"Accuracy":"77.8"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Qwen2idae-16x14B (4-shot)","rank_in_archive_order":65,"of":99,"metrics":{"Accuracy":"48.6"},"uses_additional_data":false},{"leaderboard":"/sota/code-generation-on-mbpp","task":"Code Generation","dataset":"MBPP","model":"Camelidae-8×34B (4-shot)","rank_in_archive_order":82,"of":99,"metrics":{"Accuracy":"41.4"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-challenge","task":"Common Sense Reasoning","dataset":"ARC (Challenge)","model":"Camelidae-8×34B","rank_in_archive_order":21,"of":54,"metrics":{"Accuracy":"65.2"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-arc-easy","task":"Common Sense Reasoning","dataset":"ARC (Easy)","model":"Camelidae-8×34B","rank_in_archive_order":6,"of":47,"metrics":{"Accuracy":"86.2"},"uses_additional_data":false},{"leaderboard":"/sota/common-sense-reasoning-on-winogrande","task":"Common Sense Reasoning","dataset":"WinoGrande","model":"Camelidae-8×34B","rank_in_archive_order":16,"of":77,"metrics":{"Accuracy":"80.9"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Qwen2idae-16x14B (4-shot)","rank_in_archive_order":90,"of":135,"metrics":{"Accuracy":"29.9"},"uses_additional_data":false},{"leaderboard":"/sota/math-word-problem-solving-on-math","task":"Math Word Problem Solving","dataset":"MATH","model":"Camelidae-8×34B (4-shot)","rank_in_archive_order":100,"of":135,"metrics":{"Accuracy":"22.6"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-piqa","task":"Question Answering","dataset":"PIQA","model":"Camelidae-8×34B","rank_in_archive_order":19,"of":67,"metrics":{"Accuracy":"82.7"},"uses_additional_data":false},{"leaderboard":"/sota/sentence-completion-on-hellaswag","task":"Sentence Completion","dataset":"HellaSwag","model":"Camelidae-8×34B (10-shot)","rank_in_archive_order":34,"of":89,"metrics":{"Accuracy":"83.2"},"uses_additional_data":false},{"leaderboard":"/sota/sentence-completion-on-hellaswag","task":"Sentence Completion","dataset":"HellaSwag","model":"Qwen2idae-16x14B (10-shot)","rank_in_archive_order":38,"of":89,"metrics":{"Accuracy":"82.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2401.02731","atlas_url":"https://app.syntology.ai/?focus=2401.02731","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2401.02731"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2401.02731\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2401.02731"},"call":"get_concepts_for_paper(arxiv_id=\"2401.02731\")"}],"by_repo":[{"repo":"wuhy68/parameter-efficient-moe","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"ShayekhBinIslam/openrag","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2310.11511"],"harvested_for_calls":[{"arxiv_id":"2310.11511","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2310.11511"},"call":"get_harvested_code_for_paper(arxiv_id=\"2310.11511\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c3bb0af4be6f1821c82e935f2837e2de10d19f976942a4b83f270964fbb57f14","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}