{"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/length-generalization-of-causal-transformers","title":"Length Generalization of Causal Transformers without Position Encoding","arxiv_id":"2404.12224","date":"2024-04-18","proceeding":null,"authors":["Jie Wang","Tao Ji","Yuanbin Wu","Hang Yan","Tao Gui","Qi Zhang","Xuanjing Huang","Xiaoling Wang"],"abstract":"Generalizing to longer sentences is important for recent Transformer-based language models. Besides algorithms manipulating explicit position features, the success of Transformers without position encodings (NoPE) provides a new way to overcome the challenge. In this paper, we study the length generalization property of NoPE. We find that although NoPE can extend to longer sequences than the commonly used explicit position encodings, it still has a limited context length. We identify a connection between the failure of NoPE's generalization and the distraction of attention distributions. We propose a parameter-efficient tuning for searching attention heads' best temperature hyper-parameters, which substantially expands NoPE's context size. Experiments on long sequence language modeling, the synthetic passkey retrieval task and real-world long context tasks show that NoPE can achieve competitive performances with state-of-the-art length generalization algorithms. The source code is publicly accessible","url_abs":"https://arxiv.org/abs/2404.12224v2","url_pdf":"https://arxiv.org/pdf/2404.12224v2.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":"length-generalization-of-causal-transformers","repo_url":"https://github.com/antnlp/nope_head_scale","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":null,"task_name":"Position"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.12224","atlas_url":"https://app.syntology.ai/?focus=2404.12224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12224"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/antnlp/nope_head_scale","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"official":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"3c92c963bb0cbb73","entry":"find_correction_dim","repo":"antnlp/nope_head_scale","repo_kind":"official","path":"models/LlamaYaRNScaledRotaryEmbedding.py","file_url":"https://github.com/antnlp/nope_head_scale/blob/HEAD/models/LlamaYaRNScaledRotaryEmbedding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3c92c963bb0cbb73"}},{"code_sha256_prefix":"763ecb554c17d2fe","entry":"find_correction_range","repo":"antnlp/nope_head_scale","repo_kind":"official","path":"models/LlamaYaRNScaledRotaryEmbedding.py","file_url":"https://github.com/antnlp/nope_head_scale/blob/HEAD/models/LlamaYaRNScaledRotaryEmbedding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"763ecb554c17d2fe"}},{"code_sha256_prefix":"4ea60bb6b675e2d1","entry":"get_cosine_schedule_with_warmup","repo":"antnlp/nope_head_scale","repo_kind":"official","path":"trainer.py","file_url":"https://github.com/antnlp/nope_head_scale/blob/HEAD/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ea60bb6b675e2d1"}},{"code_sha256_prefix":"5034871c1d2783cf","entry":"linear_ramp_mask","repo":"antnlp/nope_head_scale","repo_kind":"official","path":"models/LlamaYaRNScaledRotaryEmbedding.py","file_url":"https://github.com/antnlp/nope_head_scale/blob/HEAD/models/LlamaYaRNScaledRotaryEmbedding.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5034871c1d2783cf"}},{"code_sha256_prefix":"da1324ea8b806af3","entry":"compute_metrics_clm","repo":"antnlp/nope_head_scale","repo_kind":"official","path":"evals/eval_clm.py","file_url":"https://github.com/antnlp/nope_head_scale/blob/HEAD/evals/eval_clm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"da1324ea8b806af3"}},{"code_sha256_prefix":"3d16f9f93f94fd9d","entry":"compute_metrics_clm_no_early","repo":"antnlp/nope_head_scale","repo_kind":"official","path":"evals/eval_clm.py","file_url":"https://github.com/antnlp/nope_head_scale/blob/HEAD/evals/eval_clm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d16f9f93f94fd9d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}