{"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/autotinybert-automatic-hyper-parameter","title":"AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models","arxiv_id":"2107.13686","date":"2021-07-29","proceeding":"ACL 2021 5","authors":["Yichun Yin","Cheng Chen","Lifeng Shang","Xin Jiang","Xiao Chen","Qun Liu"],"abstract":"Pre-trained language models (PLMs) have achieved great success in natural language processing. Most of PLMs follow the default setting of architecture hyper-parameters (e.g., the hidden dimension is a quarter of the intermediate dimension in feed-forward sub-networks) in BERT (Devlin et al., 2019). Few studies have been conducted to explore the design of architecture hyper-parameters in BERT, especially for the more efficient PLMs with tiny sizes, which are essential for practical deployment on resource-constrained devices. In this paper, we adopt the one-shot Neural Architecture Search (NAS) to automatically search architecture hyper-parameters. Specifically, we carefully design the techniques of one-shot learning and the search space to provide an adaptive and efficient development way of tiny PLMs for various latency constraints. We name our method AutoTinyBERT and evaluate its effectiveness on the GLUE and SQuAD benchmarks. The extensive experiments show that our method outperforms both the SOTA search-based baseline (NAS-BERT) and the SOTA distillation-based methods (such as DistilBERT, TinyBERT, MiniLM and MobileBERT). In addition, based on the obtained architectures, we propose a more efficient development method that is even faster than the development of a single PLM.","url_abs":"https://arxiv.org/abs/2107.13686v1","url_pdf":"https://arxiv.org/pdf/2107.13686v1.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":"autotinybert-automatic-hyper-parameter","repo_url":"https://github.com/huawei-noah/Pretrained-Language-Model","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"one-shot-learning","task_name":"One-Shot Learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"autotinybert","method_name":"AutoTinyBERT"},{"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":"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":[{"slug":"autotinybert","name":"AutoTinyBERT","full_name":"AutoTinyBERT"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2107.13686","atlas_url":"https://app.syntology.ai/?focus=2107.13686","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":"2107.13686"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2107.13686\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2107.13686"},"call":"get_concepts_for_paper(arxiv_id=\"2107.13686\")"}],"by_repo":[{"repo":"huawei-noah/Pretrained-Language-Model","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":8,"harvested_for":["1909.10351","2004.04037","2004.11579","2010.16143","2012.15701","2101.08106","2204.00408","2307.02047"],"harvested_for_calls":[{"arxiv_id":"1909.10351","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1909.10351"},"call":"get_harvested_code_for_paper(arxiv_id=\"1909.10351\")"},{"arxiv_id":"2004.04037","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.04037"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.04037\")"},{"arxiv_id":"2004.11579","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2004.11579"},"call":"get_harvested_code_for_paper(arxiv_id=\"2004.11579\")"},{"arxiv_id":"2010.16143","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2010.16143"},"call":"get_harvested_code_for_paper(arxiv_id=\"2010.16143\")"},{"arxiv_id":"2012.15701","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2012.15701"},"call":"get_harvested_code_for_paper(arxiv_id=\"2012.15701\")"},{"arxiv_id":"2101.08106","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2101.08106"},"call":"get_harvested_code_for_paper(arxiv_id=\"2101.08106\")"},{"arxiv_id":"2204.00408","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2204.00408"},"call":"get_harvested_code_for_paper(arxiv_id=\"2204.00408\")"},{"arxiv_id":"2307.02047","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2307.02047"},"call":"get_harvested_code_for_paper(arxiv_id=\"2307.02047\")"}]}],"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":"ef3f6a66eee8cdbdb4355e55ae9cab139f8819af1b07572760b5df8006231278","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}