Papers › ByT5: Towards a token-free future with pre-trained byte-to-byte models

ByT5: Towards a token-free future with pre-trained byte-to-byte models

28 May 2021arXiv:2105.13626archive 2025-07-28

Linting Xue, Aditya Barua, Noah Constant, Rami Al-Rfou, Sharan Narang, Mihir Kale, Adam Roberts, Colin Raffel

Most widely-used pre-trained language models operate on sequences of tokens corresponding to word or subword units. By comparison, token-free models that operate directly on raw text (bytes or characters) have many benefits: they can process text in any language out of the box, they are more robust to noise, and they minimize technical debt by removing complex and error-prone text preprocessing pipelines. Since byte or character sequences are longer than token sequences, past work on token-free models has often introduced new model architectures designed to amortize the cost of operating directly on raw text. In this paper, we show that a standard Transformer architecture can be used with minimal modifications to process byte sequences. We characterize the trade-offs in terms of parameter count, training FLOPs, and inference speed, and show that byte-level models are competitive with their token-level counterparts. We also demonstrate that byte-level models are significantly more robust to noise and perform better on tasks that are sensitive to spelling and pronunciation. As part of our contribution, we release a new set of pre-trained byte-level Transformer models based on the T5 architecture, as well as all code and data used in our experiments.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 6 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 4 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/byt5 officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
ufal/multilexnorm2021 mentioned on GitHubpytorchSyntology: not harvested report
2024-MindSpore-1/Code2 mindsporeSyntology: not harvested report
huggingface/transformers jaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
yoreG123/Paddle-ByT5 paddleMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

6 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran
1unverified

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

google-research/byt5 official repository 4 samples, 4 ran (0 instrument-failed) · 0 unverified
bleu1 byt5/metrics.py ran Apache-2.0 (permissive) · fa96fb90180ccd08 · report fixture: signature targets:list/1/str, predictions:list/1/str · returned dict · level recorded 2026-09-25
cer byt5/metrics.py ran Apache-2.0 (permissive) · 31d155ca87421398 · report fixture: signature targets:list/1/str, predictions:list/1/str · returned dict · level recorded 2026-09-25
get_perc_99_len byt5/get_length_stats.py ran fingerprinted Apache-2.0 (permissive) · d47efbd10d362210 · report fixture: signature input_length:list/1/int · returned int · level recorded 2026-09-25
metrics_task1_2020 byt5/sigmorphon.py ran Apache-2.0 (permissive) · cc3b1f39907cd5aa · report fixture: signature targets:list/1/list, predictions:list/1/list · returned dict · level recorded 2026-09-25
yoreG123/Paddle-ByT5 community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
sequence_mask in 55 papers
census: 12 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
byt5/paddlenlp/layers/sequence.py ran MIT (permissive) · c5e1f47618c8fdaa · report fixture: signature seq_ids:Tensor/2/int, valid_lengths:Tensor/1/int · returned Tensor · level recorded 2026-09-24
load_vocabulary in 5 papers byt5/paddlenlp/experimental/model_utils.py unverified MIT (permissive) · 7667c4274e1b357d · report

Tasks

Cross-Lingual NERCross-Lingual Natural Language InferenceCross-Lingual Paraphrase IdentificationCross-Lingual Question AnsweringExtreme SummarizationQuestion Answering

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Lingual NER WikiAnn NER ByT5 XXL F1 67.7 #1 of 1 Archive leaderboard report
Cross-Lingual Natural Language Inference XNLI ByT5 XXL Accuracy 83.7 #1 of 5 Archive leaderboard report
Cross-Lingual Natural Language Inference XNLI ByT5 Small Accuracy 69.1 #4 of 5 Archive leaderboard report
Cross-Lingual Question Answering MLQA ByT5 XXL EM 54.9 #1 of 3 Archive leaderboard report
Cross-Lingual Question Answering MLQA ByT5 XXL F1 71.6 #1 of 3 Archive leaderboard report
Cross-Lingual Question Answering TyDiQA-GoldP ByT5 (fine-tuned) EM 81.9 #1 of 11 Archive leaderboard report
Cross-Lingual Question Answering TyDiQA-GoldP ByT5 XXL EM 60.0 #5 of 11 Archive leaderboard report
Cross-Lingual Question Answering TyDiQA-GoldP ByT5 XXL F1 75.3 #5 of 11 Archive leaderboard report
Cross-Lingual Question Answering XQuAD ByT5 XXL EM 63.6 #1 of 4 Archive leaderboard report
Cross-Lingual Question Answering XQuAD ByT5 XXL F1 79.7 #1 of 4 Archive leaderboard report
Extreme Summarization GEM-XSum ByT5 BLEU score 15.3 #5 of 6 Archive leaderboard report
Extreme Summarization GEM-XSum mT5 BLEU score 14.3 #6 of 6 Archive leaderboard report
Question Answering TweetQA ByT5 (small) BLEU-1 72.0 #1 of 3 Archive leaderboard report
Question Answering TweetQA mT5 BLEU-1 70.8 #2 of 3 Archive leaderboard report
Question Answering TweetQA mT5 ROUGE-L 74.3 #2 of 3 Archive leaderboard report
Question Answering TweetQA ByT5 ROUGE-L 75.7 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdafactorAdamAttentionAttention DropoutBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSentencePieceSoftmaxT5Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections