{"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/scaling-transformer-to-1m-tokens-and-beyond","title":"Scaling Transformer to 1M tokens and beyond with RMT","arxiv_id":"2304.11062","date":"2023-04-19","proceeding":null,"authors":["Aydar Bulatov","Yuri Kuratov","Yermek Kapushev","Mikhail S. Burtsev"],"abstract":"A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer models to extend input context length while linearly scaling compute. Our approach demonstrates the capability to store information in memory for sequences of up to an unprecedented two million tokens while maintaining high retrieval accuracy. Experiments with language modeling tasks show perplexity improvement as the number of processed input segments increases. These results underscore the effectiveness of our method, which has significant potential to enhance long-term dependency handling in natural language understanding and generation tasks, as well as enable large-scale context processing for memory-intensive applications.","url_abs":"https://arxiv.org/abs/2304.11062v2","url_pdf":"https://arxiv.org/pdf/2304.11062v2.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":"scaling-transformer-to-1m-tokens-and-beyond","repo_url":"https://github.com/booydar/t5-experiments","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"scaling-transformer-to-1m-tokens-and-beyond","repo_url":"https://github.com/booydar/lm-rmt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"scaling-transformer-to-1m-tokens-and-beyond","repo_url":"https://github.com/booydar/transformer-xl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"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":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.11062","atlas_url":"https://app.syntology.ai/?focus=2304.11062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.11062"}},"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/booydar/transformer-xl","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/booydar/t5-experiments","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/booydar/lm-rmt","reach":null}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"listed":{"samples":8,"ran":2,"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":"d142e8a68b535885","entry":"get_logger","repo":"booydar/transformer-xl","repo_kind":"listed","path":"pytorch/utils/exp_utils.py","file_url":"https://github.com/booydar/transformer-xl/blob/HEAD/pytorch/utils/exp_utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d142e8a68b535885"}},{"code_sha256_prefix":"93228a3eb5c4d179","entry":"sample_logits","repo":"booydar/transformer-xl","repo_kind":"listed","path":"pytorch/utils/log_uniform_sampler.py","file_url":"https://github.com/booydar/transformer-xl/blob/HEAD/pytorch/utils/log_uniform_sampler.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"code_sha256_prefix":"3111b71c0c6db589","entry":"create_exp_dir","repo":"booydar/transformer-xl","repo_kind":"listed","path":"pytorch/utils/exp_utils.py","file_url":"https://github.com/booydar/transformer-xl/blob/HEAD/pytorch/utils/exp_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3111b71c0c6db589"}},{"code_sha256_prefix":"e4a5158e06e5f43f","entry":"create_sequence","repo":"booydar/transformer-xl","repo_kind":"listed","path":"pytorch/experiment_utils/retrieval.py","file_url":"https://github.com/booydar/transformer-xl/blob/HEAD/pytorch/experiment_utils/retrieval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4a5158e06e5f43f"}},{"code_sha256_prefix":"c5ad9198fb1047fb","entry":"get_three_letters","repo":"booydar/transformer-xl","repo_kind":"listed","path":"pytorch/experiment_utils/retrieval.py","file_url":"https://github.com/booydar/transformer-xl/blob/HEAD/pytorch/experiment_utils/retrieval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c5ad9198fb1047fb"}},{"code_sha256_prefix":"679c549539e38322","entry":"get_three_numbers","repo":"booydar/transformer-xl","repo_kind":"listed","path":"pytorch/experiment_utils/retrieval.py","file_url":"https://github.com/booydar/transformer-xl/blob/HEAD/pytorch/experiment_utils/retrieval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"679c549539e38322"}},{"code_sha256_prefix":"69598ced7806d8c3","entry":"scatter","repo":"booydar/transformer-xl","repo_kind":"listed","path":"pytorch/utils/data_parallel.py","file_url":"https://github.com/booydar/transformer-xl/blob/HEAD/pytorch/utils/data_parallel.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"69598ced7806d8c3"}},{"code_sha256_prefix":"aa1de448b0528802","entry":"scatter_kwargs","repo":"booydar/transformer-xl","repo_kind":"listed","path":"pytorch/utils/data_parallel.py","file_url":"https://github.com/booydar/transformer-xl/blob/HEAD/pytorch/utils/data_parallel.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aa1de448b0528802"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}