Papers › Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context

9 Jan 2019ACL 2019 7arXiv:1901.02860archive 2025-07-28

Zihang Dai, Zhilin Yang, Yiming Yang, Jaime Carbonell, Quoc V. Le, Ruslan Salakhutdinov

Transformers have a potential of learning longer-term dependency, but are limited by a fixed-length context in the setting of language modeling. We propose a novel neural architecture Transformer-XL that enables learning dependency beyond a fixed length without disrupting temporal coherence. It consists of a segment-level recurrence mechanism and a novel positional encoding scheme. Our method not only enables capturing longer-term dependency, but also resolves the context fragmentation problem. As a result, Transformer-XL learns dependency that is 80% longer than RNNs and 450% longer than vanilla Transformers, achieves better performance on both short and long sequences, and is up to 1,800+ times faster than vanilla Transformers during evaluation. Notably, we improve the state-of-the-art results of bpc/perplexity to 0.99 on enwiki8, 1.08 on text8, 18.3 on WikiText-103, 21.8 on One Billion Word, and 54.5 on Penn Treebank (without finetuning). When trained only on WikiText-103, Transformer-XL manages to generate reasonably coherent, novel text articles with thousands of tokens. Our code, pretrained models, and hyperparameters are available in both Tensorflow and PyTorch.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 143 code samples: 141 from 20 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 143: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 12 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 8 ran (7 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 128 samples from 19 repositories, 57 ran (41 with no instrument failure; 16 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

37 repositories listed; official and paper-mentioned ones first.

kimiyoung/transformer-xl officialmentioned in papermentioned on GitHubpytorchSyntology: 13 samples, 8 ran (1 instrument-failed) · 5 unverified report
Jmkernes/PAR-Transformer-XL mentioned on GitHubtfSyntology: 11 samples, 7 ran (4 instrument-failed) · 4 unverified report
Machine-Learning-Tokyo/Poetry-GAN mentioned on GitHubMITSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
SambhawDrag/XLNet.jl mentioned on GitHubpytorchSyntology: not harvested report
TimDettmers/transformer-xl mentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 2 ran (0 instrument-failed) · 10 unverified report
aiha-lab/Attention-Head-Pruning mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
benkrause/dynamiceval-transformer mentioned on GitHubtfSyntology: 12 samples, 4 ran (4 instrument-failed) · 8 unverified report
cedrickchee/pytorch-pretrained-BERT mentioned on GitHubpytorchSyntology: 17 samples, 4 ran (1 instrument-failed) · 13 unverified report
cmunnis/BERT_vs_Transformer-XL mentioned on GitHubpytorchSyntology: not harvested report
facebookresearch/code-prediction-transformer mentioned on GitHubpytorchSyntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
google-research/meliad mentioned on GitHubjaxApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Memorizing Transformers (arXiv:2203.08913; that paper's own run record: 23 ran (of which 6 constructed an object rather than computing a result; 18 with no instrument failure: 3 honoured, 1 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
huggingface/transformers mentioned on GitHubpytorchSyntology: 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
huggingface/xlnet mentioned on GitHubtfSyntology: 13 samples, 4 ran (3 instrument-failed) · 9 unverified report
inzva/fake-academic-paper-generation mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
listenviolet/XLNet mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
mustafaaljadery/gemma-2b-10m mentioned on GitHubpytorchSyntology: 7 samples, 4 ran (1 instrument-failed) · 3 unverified report
okkteam/Transformer-Transducer mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
park-cheol/ASR-Conformer mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
samwisegamjeee/pytorch-transformers mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to XLNet: Generalized Autoregressive Pretraining for Language Understanding (arXiv:1906.08237; that paper's own run record: 15 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
sh951011/Attention-Implementation mentioned on GitHubpytorchMITSyntology: not harvested report
shanghai-digital-brain-laboratory/bdm-db1 mentioned on GitHubpytorchSyntology: 14 samples, 10 ran (0 instrument-failed) · 4 unverified report
sooftware/Attention-Implementation mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
sooftware/attentions mentioned on GitHubpytorchMITSyntology: not harvested report
sooftware/conformer mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
sooftware/nlp-attentions mentioned on GitHubpytorchMITSyntology: not harvested report
wxt1997/Transformer-Transducer mentioned on GitHubpytorchSyntology: not harvested report
zhdbwe/Paper-DailyReading mentioned on GitHubtfSyntology: not harvested report
2023-MindSpore-1/ms-code-220 mindsporeSyntology: not harvested report
AIResearchHub/transformergallery pytorchSyntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
NVIDIA/DeepLearningExamples pytorchSyntology: 11 samples, 4 ran (0 instrument-failed) · 7 unverified report
NVIDIA/DeepLearningExamples pytorchSyntology: 11 samples, 4 ran (0 instrument-failed) · 7 unverified report
PaddlePaddle/PaddleNLP paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation... (arXiv:2301.03416; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
jiean001/models_m mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HyperText: Endowing FastText with Hyperbolic Geometry (arXiv:2010.16143; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
jincan333/lot pytorchSyntology: 2 samples, 0 ran · 2 unverified report
labmlai/annotated_deep_learning_paper_implementations pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Playing Atari with Deep Reinforcement Learning (arXiv:1312.5602; that paper's own run record: 64 ran (of which 24 constructed an object rather than computing a result; 46 with no instrument failure: 5 honoured, 0 violated, 41 with no contract checked; 18 where Syntology's instrument failed) · 53 unverified), Adam: A Method for Stochastic Optimization (arXiv:1412.6980; that paper's own run record: 27 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 4 honoured, 2 violated, 17 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified), Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified) and 12 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
lvyufeng/bert4ms mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RoBERTa: A Robustly Optimized BERT Pretraining Approach (arXiv:1907.11692; that paper's own run record: 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
opendilab/DI-engine pytorchSyntology: 5 samples, 3 ran (3 instrument-failed) · 2 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

143 samples harvested: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 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.

4ran · honoured contract
1ran · violated contract
6ran · our draft was wrong
12ran; the contract check could not run
44ran
76unverified

Licence: 43 of the 143 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 20 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. 2 samples are listed last, in a group without a repository. “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”. For 10 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

kimiyoung/transformer-xl official repository 13 samples, 8 ran (1 instrument-failed) · 5 unverified
AdaptiveEmbedding pytorch/mem_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 1ae137f0cee15e33 · report fixture: returned AdaptiveEmbedding · level recorded 2026-09-22
DecoderLayer in 43 papers pytorch/mem_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · e8aac29a19d0c2e7 · report fixture: returned DecoderLayer · level recorded 2026-09-22
LogUniformSampler pytorch/mem_transformer.py ran Apache-2.0 (permissive) · 220657028509cfb1 · report fixture: returned LogUniformSampler · level recorded 2026-09-22
MultiHeadAttn in 5 papers pytorch/mem_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · d99c9cc9af9de483 · report fixture: returned MultiHeadAttn · level recorded 2026-09-22
PositionwiseFF pytorch/mem_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · c96fba039a607703 · report fixture: returned PositionwiseFF · level recorded 2026-09-22
ProjectedAdaptiveLogSoftmax pytorch/mem_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 338c39719307318d · report fixture: returned ProjectedAdaptiveLogSoftmax · level recorded 2026-09-22
RelMultiHeadAttn pytorch/mem_transformer.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · fe28ba867add05c0 · report fixture: returned RelMultiHeadAttn · level recorded 2026-09-22
sample_logits in 16 papers pytorch/mem_transformer.py ran · our draft was wrong Apache-2.0 (permissive) · 93228a3eb5c4d179 · report fixture: signature embedding:callable/0/?, bias:Tensor/1/float, labels:Tensor/2/int, inputs:Tensor/3/float, sampler:LogUniformSampler/0/? · returned Tensor · level recorded 2026-09-22
MemTransformerLM pytorch/mem_transformer.py unverified Apache-2.0 (permissive) · 9ef2fc89678fefb2 · report
RelLearnableDecoderLayer pytorch/mem_transformer.py unverified Apache-2.0 (permissive) · 17ee18e7e701439f · report
RelLearnableMultiHeadAttn pytorch/mem_transformer.py unverified Apache-2.0 (permissive) · a033a134e9f6452f · report
RelPartialLearnableDecoderLayer pytorch/mem_transformer.py unverified Apache-2.0 (permissive) · 89afd0bff30e18a9 · report
RelPartialLearnableMultiHeadAttn in 5 papers pytorch/mem_transformer.py unverified Apache-2.0 (permissive) · fb613dd5bc21371c · report
Jmkernes/PAR-Transformer-XL community (archive-listed) 11 samples, 7 ran (4 instrument-failed) · 4 unverified
RelMultiHeadAttention par_model.py ran no licence file found · pointer only · 4c8b264bb79a35a1 · report fixture: returned RelMultiHeadAttention · level recorded 2026-09-22
create_lookahead_mask par_model.py ran · honoured contract no licence file found · pointer only · 499bf5fee7915c78 · report fixture: signature query_len:int/0/int, key_len:int/0/int, dtype:DType/0/? · returned EagerTensor · level recorded 2026-09-22
left_shift par_model.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 8d59a6d5900428f5 · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
positional_encoding in 63 papers
census: 5 implementations from 6 papers, 4 distinct outputs on one shared input
par_model.py ran · honoured contract fingerprinted no licence file found · pointer only · 2398c4a5c285bdc4 · report fixture: signature max_position:int/0/int, d_embed:int/0/int, min_freq:float/0/float · returned EagerTensor · level recorded 2026-09-22
positionwise_ffn par_model.py ran · our draft was wrong no licence file found · pointer only · f7a746d73ab2f28c · report fixture: signature d_model:int/0/int, d_fnn:int/0/int, activation:str/0/str · returned Sequential · level recorded 2026-09-22
relative_position_logits par_model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · edeef97857b7cdca · report fixture: signature q:EagerTensor/4/float, R:EagerTensor/4/float, direction:str/0/str · returned EagerTensor · level recorded 2026-09-22
right_shift in 7 papers par_model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · df4647a6d9f03c0e · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
AdaptiveSoftmax par_model.py unverified no licence file found · pointer only · 87202268910cb496 · report
PARTransformerXL par_model.py unverified no licence file found · pointer only · de3ab66ec62fc167 · report
RelaxedOneHot par_model.py unverified no licence file found · pointer only · 1be1a875d12d10b3 · report
StochasticBlock par_model.py unverified no licence file found · pointer only · 534b6317f069c394 · report
Machine-Learning-Tokyo/Poetry-GAN community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
post_process in 56 papers lang_model.py ran fingerprinted MIT (permissive) · 9d6735f22035b700 · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-24
lm_loss textgan.py unverified MIT (permissive) · c1c98338b80e7459 · report
seq_gumbel_softmax textgan.py unverified MIT (permissive) · e7ebaba541ff0216 · report
TimDettmers/transformer-xl community (archive-listed) 12 samples, 2 ran (0 instrument-failed) · 10 unverified
assign_to_gpu tf/gpu_utils.py ran Apache-2.0 (permissive) · 6b2a8f1c93d0b071 · report fixture: signature gpu:int/0/int, ps_dev:str/0/str · returned function · level recorded 2026-09-25
batchify in 71 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
tf/data_utils.py ran Apache-2.0 (permissive) · 36eed0b265968be7 · report fixture: signature data:ndarray/1/int, batch_size:int/0/int, num_passes:int/0/int · returned ndarray · level recorded 2026-09-26
average_grads_and_vars tf/gpu_utils.py unverified Apache-2.0 (permissive) · 0e3f1e158da4c3b8 · report
checkpoint_exists tf/avg_checkpoints.py unverified Apache-2.0 (permissive) · e505aeb6374f0f1c · report
create_ordered_tfrecords tf/data_utils.py unverified Apache-2.0 (permissive) · 48246428164ddbc5 · report
generate_per_core_enqueue_ops_fn_for_host tf/tpu_estimator.py unverified Apache-2.0 (permissive) · f07d3c5f67c9a93d · report
generate_per_host_enqueue_ops_fn_for_host tf/tpu_estimator.py unverified Apache-2.0 (permissive) · d5a05e8b3b59f012 · report
generate_per_host_v2_enqueue_ops_fn_for_host tf/tpu_estimator.py unverified Apache-2.0 (permissive) · 8ca3ba583d69ea38 · report
get_bin_sizes tf/data_utils.py unverified Apache-2.0 (permissive) · ab8eff277d0925e9 · report
load_from_checkpoint in 9 papers tf/gpu_utils.py unverified Apache-2.0 (permissive) · 3d6b054785523852 · report
scatter in 33 papers pytorch/utils/data_parallel.py unverified Apache-2.0 (permissive) · 69598ced7806d8c3 · report
scatter_kwargs in 17 papers pytorch/utils/data_parallel.py unverified Apache-2.0 (permissive) · aa1de448b0528802 · report
benkrause/dynamiceval-transformer community (archive-listed) 12 samples, 4 ran (4 instrument-failed) · 8 unverified
_cache_mem tf/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 773651748c9618d6 · report fixture: signature curr_out:EagerTensor/2/float, prev_mem:EagerTensor/2/float, mem_len:int/0/int · returned EagerTensor · level recorded 2026-09-22
embedding_lookup in 9 papers tf/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · 9109ba9791e44324 · report fixture: signature lookup_table:EagerTensor/2/float, x:EagerTensor/2/int, use_tpu:bool/0/bool · returned EagerTensor · level recorded 2026-09-22
positional_embedding tf/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · d50e8679cde3a927 · report fixture: signature pos_seq:EagerTensor/1/float, inv_freq:EagerTensor/1/float, bsz:int/0/int · returned EagerTensor · level recorded 2026-09-22
rel_shift tf/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · d37883dc58ff9b69 · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-22
_create_mask tf/model.py unverified Apache-2.0 (permissive) · ed15761e38990647 · report
mask_adaptive_embedding_lookup tf/model.py unverified Apache-2.0 (permissive) · 99e35dc770639097 · report
mask_adaptive_logsoftmax tf/model.py unverified Apache-2.0 (permissive) · fca4d6d03913ae24 · report
mul_adaptive_embedding_lookup tf/model.py unverified Apache-2.0 (permissive) · 8d07f1308bd24cbc · report
mul_adaptive_logsoftmax tf/model.py unverified Apache-2.0 (permissive) · e344186184b46850 · report
positionwise_FF tf/model.py unverified Apache-2.0 (permissive) · 3652bf001c221967 · report
rel_multihead_attn tf/model.py unverified Apache-2.0 (permissive) · b1f1afea05cd968b · report
transformer in 16 papers tf/model.py unverified Apache-2.0 (permissive) · d0f56431ab6c3b37 · report
cedrickchee/pytorch-pretrained-BERT community (archive-listed) 17 samples, 4 ran (1 instrument-failed) · 13 unverified
AdaptiveEmbedding pytorch_pretrained_bert/modeling_transfo_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · e77541c1b4b15830 · report fixture: returned AdaptiveEmbedding · level recorded 2026-09-22
PositionalEmbedding in 43 papers
census: 6 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
pytorch_pretrained_bert/modeling_transfo_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 06ce2b899569db5b · report fixture: returned PositionalEmbedding · level recorded 2026-09-22
TransfoXLConfig pytorch_pretrained_bert/modeling_transfo_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · a97a22ac6fb31922 · report fixture: returned TransfoXLConfig · level recorded 2026-09-22
build_tf_to_pytorch_map in 14 papers pytorch_pretrained_bert/modeling_transfo_xl.py ran · our draft was wrong Apache-2.0 (permissive) · 35ef111fc00c21b4 · report fixture: signature model:callable/0/?, config:Config/0/? · returned dict · level recorded 2026-09-22
DecoderLayer in 43 papers pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · fc52846dc775edff · report
MultiHeadAttn in 5 papers pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · d4857f57ecefa3d5 · report
PositionwiseFF pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · 62b1b4ab79fdfc8b · report
RelLearnableDecoderLayer pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · 752529d23a4b3b22 · report
RelLearnableMultiHeadAttn pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · 3dafbc50941af43d · report
RelMultiHeadAttn pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · dc7c9e91c34d6ddf · report
RelPartialLearnableDecoderLayer pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · fd8d58e6a1428332 · report
RelPartialLearnableMultiHeadAttn in 5 papers pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · 8361fa24d3e06e13 · report
TransfoXLModel pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · 532a59e61c71b7a8 · report
TransfoXLPreTrainedModel pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · d7bd7d30264b3658 · report
cached_path in 47 papers pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · 6fee57012e68e835 · report
get_from_cache pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · b4bb49d2de702f67 · report
load_tf_weights_in_transfo_xl in 12 papers pytorch_pretrained_bert/modeling_transfo_xl.py unverified Apache-2.0 (permissive) · 1ebc2bf2c3cddc4d · report
facebookresearch/code-prediction-transformer community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
model.py ran licence not identified · pointer only · e3217ee8bd314909 · report fixture: returned Attention · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
model.py ran licence not identified · pointer only · 548da299b3bc04e9 · report fixture: returned Block · level recorded 2026-09-22
GPT2Model model.py ran licence not identified · pointer only · 72ccb5501088c2b4 · report fixture: returned GPT2Model · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
model.py ran licence not identified · pointer only · 39480331817170e8 · report fixture: returned LayerNorm · level recorded 2026-09-22
MLP in 375 papers model.py ran licence not identified · pointer only · df5a6cf54dd0aca6 · report fixture: returned MLP · level recorded 2026-09-22
PathLSTM model.py ran licence not identified · pointer only · 5fb8aacfbced509d · report fixture: returned PathLSTM · level recorded 2026-09-22
GPT2LMHead model.py unverified licence not identified · pointer only · 117b06ce2fbc7877 · report
TransformerModel in 26 papers model.py unverified licence not identified · pointer only · 9a2f71717dcf3962 · report
huggingface/xlnet community (archive-listed) 13 samples, 4 ran (3 instrument-failed) · 9 unverified
_cache_mem modeling.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 9d5e914b24b8911a · report fixture: signature curr_out:EagerTensor/2/float, prev_mem:EagerTensor/2/float, mem_len:int/0/int, reuse_len:int/0/int · returned EagerTensor · level recorded 2026-09-22
positional_embedding modeling.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 9bf0f6e6298f3fbe · report fixture: signature pos_seq:EagerTensor/1/float, inv_freq:EagerTensor/1/float, bsz:int/0/int · returned EagerTensor · level recorded 2026-09-22
rel_shift modeling.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 5f7c5b38aeb29bf5 · report fixture: signature x:EagerTensor/4/float, klen:int/0/int · returned EagerTensor · level recorded 2026-09-22
relative_positional_encoding modeling.py ran · honoured contract Apache-2.0 (permissive) · 8e76562720b0c921 · report fixture: signature qlen:int/0/int, klen:int/0/int, d_model:int/0/int, clamp_len:int/0/int, attn_type:str/0/str, bi_data:bool/0/bool, bsz:int/0/int, dtype:DType/0/? · returned EagerTensor · level recorded 2026-09-22
_create_mask modeling.py unverified Apache-2.0 (permissive) · c1f8a649a7a837d5 · report
embedding_lookup in 9 papers modeling.py unverified Apache-2.0 (permissive) · 5abf0267f0fc7514 · report
head_projection modeling.py unverified Apache-2.0 (permissive) · 6804d62cb7cd8df3 · report
positionwise_ffn modeling.py unverified Apache-2.0 (permissive) · ddf11fc956cd28ce · report
post_attention modeling.py unverified Apache-2.0 (permissive) · cf208c8c20d52c1b · report
rel_attn_core modeling.py unverified Apache-2.0 (permissive) · b517847a8c809203 · report
rel_multihead_attn modeling.py unverified Apache-2.0 (permissive) · 6ccb8d28491109b6 · report
transformer_xl modeling.py unverified Apache-2.0 (permissive) · d077730400326171 · report
two_stream_rel_attn modeling.py unverified Apache-2.0 (permissive) · 2d935f29546db9cd · report
inzva/fake-academic-paper-generation community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
ProjectedAdaptiveLogSoftmax transformer-xl/pytorch/mem_transformer.py ran MIT (permissive) · 7d9e9736e6c57d11 · report fixture: returned ProjectedAdaptiveLogSoftmax · level recorded 2026-09-22
MemTransformerLM transformer-xl/pytorch/mem_transformer.py unverified MIT (permissive) · a7430322070cedb5 · report
listenviolet/XLNet community (archive-listed) 1 sample, 0 ran · 1 unverified
XLNet xlnet.py unverified Apache-2.0 (permissive) · 2b646a664c00ffa8 · report
mustafaaljadery/gemma-2b-10m community (archive-listed) 7 samples, 4 ran (1 instrument-failed) · 3 unverified
GemmaConfig src/gemma.py ran no licence file found · pointer only · 709b8a145b15f0ca · report fixture: returned GemmaConfig · level recorded 2026-09-22
GemmaRotaryEmbedding src/gemma.py ran · metamorphic tier: deterministic no licence file found · pointer only · 39c5be8f7b1c0490 · report fixture: returned GemmaRotaryEmbedding · level recorded 2026-09-22
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
src/gemma.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 4e762613ee907cdb · report fixture: signature hidden_states:Tensor/4/float, n_rep:int/0/int · returned Tensor · level recorded 2026-09-22
rotate_half in 424 papers
census: 24 implementations from 96 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
src/gemma.py ran · honoured contract fingerprinted no licence file found · pointer only · cec833a99feb528c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GemmaAttention src/gemma.py unverified no licence file found · pointer only · e4e12108c18eb032 · report
GemmaInfiniAttention src/gemma.py unverified no licence file found · pointer only · de07f82e734e3e2c · report
okkteam/Transformer-Transducer community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
MultiHeadedAttention in 38 papers tt/transformer/attention.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5597fd8e1219b866 · report fixture: returned MultiHeadedAttention · level recorded 2026-09-22
RelPositionMultiHeadedAttention tt/transformer/attention.py ran · metamorphic tier: deterministic no licence file found · pointer only · 4977fa89216a56fa · report fixture: returned RelPositionMultiHeadedAttention · level recorded 2026-09-22
park-cheol/ASR-Conformer community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Linear in 127 papers model/attention.py ran · metamorphic tier: invariant no licence file found · pointer only · 84585e9be4407fc4 · report fixture: signature inputs:Tensor/2/float · returned Tensor · level recorded 2026-09-22
RelativeMultiHeadAttention model/attention.py ran · metamorphic tier: invariant no licence file found · pointer only · 032b78da6979837c · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, pos_embedding:Tensor/3/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
shanghai-digital-brain-laboratory/bdm-db1 community (archive-listed) 14 samples, 10 ran (0 instrument-failed) · 4 unverified
GEGLU in 20 papers
census: 12 implementations from 12 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
src/model/transformer_xl.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 845f84e3a319753d · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
GatoInputBase src/model/transformer_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 6a748d270690866b · report fixture: returned GatoInputBase · level recorded 2026-09-22
ICTaskInput src/model/transformer_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · ad41eff0feadfd69 · report fixture: returned ICTaskInput · level recorded 2026-09-22
NLPTaskInput src/model/transformer_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 7eb33bec45fe09f3 · report fixture: returned NLPTaskInput · level recorded 2026-09-22
PatchEmbeddings in 5 papers src/model/transformer_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · b54068382071f8c8 · report fixture: returned PatchEmbeddings · level recorded 2026-09-22
PositionalEmbedding in 43 papers
census: 6 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
src/model/transformer_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 142586d370dc7c1e · report fixture: returned PositionalEmbedding · level recorded 2026-09-22
PositionwiseFF src/model/transformer_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · eed8c286b97219b7 · report fixture: returned PositionwiseFF · level recorded 2026-09-22
RLTaskInput src/model/transformer_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2e57dbd19f63d3f4 · report fixture: returned RLTaskInput · level recorded 2026-09-22
VQATaskInput src/model/transformer_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2a023fc4bac8d229 · report fixture: returned VQATaskInput · level recorded 2026-09-22
VisionEmbedding src/model/transformer_xl.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 2a5f4bac2414eb0f · report fixture: returned VisionEmbedding · level recorded 2026-09-22
RelPartialLearnableDecoderLayer src/model/transformer_xl.py unverified Apache-2.0 (permissive) · 9ec384a6bfe40952 · report
RelPartialLearnableMultiHeadAttn in 5 papers src/model/transformer_xl.py unverified Apache-2.0 (permissive) · fdc345d0da45dd95 · report
TransformerXL src/model/transformer_xl.py unverified Apache-2.0 (permissive) · a2315dc06271216b · report
print_with_rank src/model/transformer_xl.py unverified Apache-2.0 (permissive) · bf75653cc30018e0 · report
sooftware/Attention-Implementation community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
RelativeMultiHeadAttention attentions.py ran MIT (permissive) · c018d465b6253b94 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, pos_embedding:Tensor/3/float, mask:Tensor/3/bool · returned Tensor · level recorded 2026-09-24
sooftware/conformer community (archive-listed) 1 sample, 0 ran · 1 unverified
RelativeMultiHeadAttention conformer/attention.py unverified Apache-2.0 (permissive) · 274ae09f88dbb42a · report
AIResearchHub/transformergallery community (archive-listed) 4 samples, 2 ran (0 instrument-failed) · 2 unverified
PositionalEncoding in 126 papers
census: 13 implementations from 9 papers, 9 distinct outputs across 5 buckets, one shared input per bucket
transformer/transformerxl.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 07bf8cf6e731d1bc · report fixture: returned PositionalEncoding · level recorded 2026-09-22
TransformerEmbedding transformer/transformerxl.py ran · metamorphic tier: deterministic MIT (permissive) · c7b5eb55f15a37de · report fixture: returned TransformerEmbedding · level recorded 2026-09-22
TransformerXL transformer/transformerxl.py unverified MIT (permissive) · fa690903d5ea5d89 · report
XLAttentionLayer transformer/transformerxl.py unverified MIT (permissive) · 91e5af7605c83b9a · report
NVIDIA/DeepLearningExamples community (archive-listed) 11 samples, 4 ran (0 instrument-failed) · 7 unverified
AdaptiveEmbedding PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8a8691f05cb1b5da · report fixture: returned AdaptiveEmbedding · level recorded 2026-09-22
MultiHeadAttn in 5 papers PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · e672e8a20905b62b · report fixture: returned MultiHeadAttn · level recorded 2026-09-22
ProjectedAdaptiveLogSoftmax PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 4088ee884194d7c4 · report fixture: returned ProjectedAdaptiveLogSoftmax · level recorded 2026-09-22
RelMultiHeadAttn PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8fa37260188b5fd8 · report fixture: returned RelMultiHeadAttn · level recorded 2026-09-22
DecoderLayer in 43 papers PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py unverified no licence file found · pointer only · c614edf5b8c0d3b0 · report
MemTransformerLM PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py unverified no licence file found · pointer only · 5ffa84d26ba39532 · report
RelLearnableDecoderLayer PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py unverified no licence file found · pointer only · ea7c8500cbc85ff5 · report
RelLearnableMultiHeadAttn PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py unverified no licence file found · pointer only · cb862dd19b1f381a · report
RelPartialLearnableDecoderLayer PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py unverified no licence file found · pointer only · 5014b04d3358c101 · report
RelPartialLearnableMultiHeadAttn in 5 papers PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py unverified no licence file found · pointer only · 5e1b71bde76b69e7 · report
sample_logits in 16 papers PyTorch/LanguageModeling/Transformer-XL/pytorch/mem_transformer.py unverified no licence file found · pointer only · 582150577e5bd769 · report
jincan333/lot community (archive-listed) 2 samples, 0 ran · 2 unverified
MemTransformerLM model/mem_transformer.py unverified MIT (permissive) · 12dd38874c15490a · report
ProjectedAdaptiveLogSoftmax model/mem_transformer.py unverified MIT (permissive) · 6b820cc9aac66bc1 · report
opendilab/DI-engine community (archive-listed) 5 samples, 3 ran (3 instrument-failed) · 2 unverified
build_normalization ding/torch_utils/network/transformer.py ran · our draft was wrong Apache-2.0 (permissive) · c92e4fc990bba2fe · report fixture: signature norm_type:str/0/str, dim:int/0/int · returned type · level recorded 2026-09-22
fc_block ding/torch_utils/network/transformer.py ran · our draft was wrong Apache-2.0 (permissive) · c1184d27672a7461 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, activation:callable/0/?, norm_type:str/0/str, use_dropout:bool/0/bool, dropout_probability:float/0/float · returned Sequential · level recorded 2026-09-22
sequential_pack ding/torch_utils/network/transformer.py ran · our draft was wrong Apache-2.0 (permissive) · a4f0d0fb0e45662a · report fixture: signature layers:list/1/callable · returned Sequential · level recorded 2026-09-22
TransformerLayer in 34 papers ding/torch_utils/network/transformer.py unverified Apache-2.0 (permissive) · b28585d20fefea46 · report
Repository not located 2 samples, 2 ran (1 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
add_and_scale repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · 78d91efd74e4d12a · report fixture: returned Tensor · level recorded 2026-09-22
to_2tuple in 25 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 4e978f9f7835b10a · report fixture: signature x:int/0/int · returned tuple · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

18 assemblies on this paper: 18 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

18 sibling assemblies for Transformer-XL (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 18 sibling assemblies; the other 6 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 15 bricks; individually on a fixture: 11 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. TransformerXL entry · level 0 · unverified · a2315dc06271216b
  2. GatoInputBase helper · level 1 · ran · 6a748d270690866b
  3. ICTaskInput helper · level 1 · ran · ad41eff0feadfd69
  4. NLPTaskInput helper · level 1 · ran · 7eb33bec45fe09f3
  5. PositionalEmbedding model · level 1 · ran · 142586d370dc7c1e
  6. RLTaskInput helper · level 1 · ran · 2e57dbd19f63d3f4
  7. RelPartialLearnableDecoderLayer model · level 0 · unverified · 9ec384a6bfe40952
  8. VQATaskInput helper · level 1 · ran · 2a023fc4bac8d229
  9. VisionEmbedding helper · level 1 · ran · 2a5f4bac2414eb0f
  10. print_with_rank helper · level 0 · unverified · bf75653cc30018e0
  11. PositionwiseFF model · level 1 · ran · eed8c286b97219b7
  12. RelPartialLearnableMultiHeadAttn model · level 0 · unverified · fdc345d0da45dd95
  13. PatchEmbeddings helper · level 1 · ran · b54068382071f8c8
  14. to_2tuple helper · level 1 · ran · violated contract · 4e978f9f7835b10a
  15. GEGLU helper · level 1 · ran · 845f84e3a319753d

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 23 bricks; individually on a fixture: 6 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 17 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. TransfoXLModel entry · level 0 · unverified · 532a59e61c71b7a8
  2. AdaptiveEmbedding model · level 1 · ran · e77541c1b4b15830
  3. DecoderLayer helper · level 0 · unverified · fc52846dc775edff
  4. PositionalEmbedding helper · level 1 · ran · 06ce2b899569db5b
  5. RelLearnableDecoderLayer model · level 0 · unverified · 752529d23a4b3b22
  6. RelPartialLearnableDecoderLayer model · level 0 · unverified · fd8d58e6a1428332
  7. TransfoXLPreTrainedModel helper · level 0 · unverified · d7bd7d30264b3658
  8. MultiHeadAttn helper · level 0 · unverified · d4857f57ecefa3d5
  9. PositionwiseFF helper · level 0 · unverified · 62b1b4ab79fdfc8b
  10. RelLearnableMultiHeadAttn model · level 0 · unverified · 3dafbc50941af43d
  11. RelPartialLearnableMultiHeadAttn model · level 0 · unverified · 8361fa24d3e06e13
  12. TransfoXLConfig helper · level 1 · ran · a97a22ac6fb31922
  13. cached_path helper · level 0 · unverified · 6fee57012e68e835
  14. load_tf_weights_in_transfo_xl helper · level 0 · unverified · 1ebc2bf2c3cddc4d
  15. RelMultiHeadAttn model · level 0 · unverified · dc7c9e91c34d6ddf
  16. get_from_cache helper · level 0 · unverified · b4bb49d2de702f67
  17. build_tf_to_pytorch_map helper · level 1 · ran · our draft was wrong · 35ef111fc00c21b4
  18. http_get helper · level 0 · unverified · 18f49ada16168f38
  19. s3_etag helper · level 0 · unverified · 51dd06ec77c8a8d1
  20. s3_get helper · level 0 · unverified · 1079045e75efbf23
  21. url_to_filename helper · level 1 · ran · our draft was wrong · 5eff22fa0a651276
  22. s3_request helper · level 1 · ran · our draft was wrong · 7661139be003d514
  23. split_s3_path helper · level 0 · unverified · d3852f416bfe86c3

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. RelativeMultiHeadAttention entry · level 1 · ran · c018d465b6253b94

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 14 bricks; individually on a fixture: 9 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. MemTransformerLM entry · level 0 · unverified · 9ef2fc89678fefb2
  2. AdaptiveEmbedding model · level 1 · ran · 1ae137f0cee15e33
  3. DecoderLayer model · level 1 · ran · e8aac29a19d0c2e7
  4. LogUniformSampler helper · level 1 · ran · 220657028509cfb1
  5. PositionalEmbedding helper · level 1 · ran · 06ce2b899569db5b
  6. ProjectedAdaptiveLogSoftmax helper · level 1 · ran · 338c39719307318d
  7. RelLearnableDecoderLayer model · level 0 · unverified · 17ee18e7e701439f
  8. RelPartialLearnableDecoderLayer model · level 0 · unverified · 89afd0bff30e18a9
  9. sample_logits helper · level 1 · ran · our draft was wrong · 93228a3eb5c4d179
  10. MultiHeadAttn helper · level 1 · ran · d99c9cc9af9de483
  11. PositionwiseFF helper · level 1 · ran · c96fba039a607703
  12. RelLearnableMultiHeadAttn model · level 0 · unverified · a033a134e9f6452f
  13. RelPartialLearnableMultiHeadAttn model · level 0 · unverified · fb613dd5bc21371c
  14. RelMultiHeadAttn model · level 1 · ran · fe28ba867add05c0

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 12 bricks; individually on a fixture: 4 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; 4 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. transformer entry · level 0 · unverified · d0f56431ab6c3b37
  2. _cache_mem model · level 1 · ran; the contract check could not run (RAISES) · 773651748c9618d6
  3. _create_mask helper · level 0 · unverified · ed15761e38990647
  4. mask_adaptive_embedding_lookup helper · level 0 · unverified · 99e35dc770639097
  5. mask_adaptive_logsoftmax helper · level 0 · unverified · fca4d6d03913ae24
  6. mul_adaptive_embedding_lookup helper · level 0 · unverified · 8d07f1308bd24cbc
  7. mul_adaptive_logsoftmax helper · level 0 · unverified · e344186184b46850
  8. positional_embedding model · level 1 · ran; the contract check could not run (RAISES) · d50e8679cde3a927
  9. positionwise_FF model · level 0 · unverified · 3652bf001c221967
  10. rel_multihead_attn model · level 0 · unverified · b1f1afea05cd968b
  11. embedding_lookup helper · level 1 · ran; the contract check could not run (RAISES) · 9109ba9791e44324
  12. rel_shift model · level 1 · ran; the contract check could not run (RAISES) · d37883dc58ff9b69

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 11 bricks; individually on a fixture: 7 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. PARTransformerXL entry · level 0 · unverified · de3ab66ec62fc167
  2. AdaptiveSoftmax model · level 0 · unverified · 87202268910cb496
  3. StochasticBlock model · level 0 · unverified · 534b6317f069c394
  4. RelMultiHeadAttention model · level 1 · ran · 4c8b264bb79a35a1
  5. RelaxedOneHot helper · level 0 · unverified · 1be1a875d12d10b3
  6. positionwise_ffn model · level 1 · ran · our draft was wrong · f7a746d73ab2f28c
  7. create_lookahead_mask helper · level 1 · ran · honoured contract · 499bf5fee7915c78
  8. positional_encoding helper · level 1 · ran · honoured contract · 2398c4a5c285bdc4
  9. relative_position_logits helper · level 1 · ran; the contract check could not run (RAISES) · edeef97857b7cdca
  10. left_shift helper · level 1 · ran; the contract check could not run (RAISES) · 8d59a6d5900428f5
  11. right_shift helper · level 1 · ran; the contract check could not run (RAISES) · df4647a6d9f03c0e

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 18 siblings

  1. RelPositionMultiHeadedAttention entry · level 1 · ran · 4977fa89216a56fa
  2. MultiHeadedAttention helper · level 1 · ran · 5597fd8e1219b866

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 7 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. GemmaInfiniAttention entry · level 0 · unverified · de07f82e734e3e2c
  2. GemmaAttention helper · level 0 · unverified · e4e12108c18eb032
  3. GemmaConfig helper · level 1 · ran · 709b8a145b15f0ca
  4. GemmaRotaryEmbedding helper · level 1 · ran · 39c5be8f7b1c0490
  5. apply_rotary_pos_emb helper · level 0 · unverified · 5c61a4c30ce59547
  6. repeat_kv helper · level 1 · ran; the contract check could not run (RAISES) · 4e762613ee907cdb
  7. rotate_half helper · level 1 · ran · honoured contract · cec833a99feb528c

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 6 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 18 siblings

  1. TransformerXL entry · level 0 · unverified · fa690903d5ea5d89
  2. TransformerEmbedding helper · level 1 · ran · c7b5eb55f15a37de
  3. XLAttentionLayer model · level 0 · unverified · 91e5af7605c83b9a
  4. PositionalEncoding helper · level 1 · ran · 07bf8cf6e731d1bc
  5. TokenEmbedding helper · level 1 · ran · 0840d53a3e87bbd0
  6. FeedForward helper · level 1 · ran · 2893a3bddf619d82

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 16 bricks; individually on a fixture: 8 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. MemTransformerLM entry · level 0 · unverified · 5ffa84d26ba39532
  2. AdaptiveEmbedding model · level 1 · ran · 8a8691f05cb1b5da
  3. DecoderLayer model · level 0 · unverified · c614edf5b8c0d3b0
  4. LogUniformSampler helper · level 1 · ran · 220657028509cfb1
  5. PositionalEmbedding helper · level 1 · ran · 06ce2b899569db5b
  6. ProjectedAdaptiveLogSoftmax helper · level 1 · ran · 4088ee884194d7c4
  7. RelLearnableDecoderLayer model · level 0 · unverified · ea7c8500cbc85ff5
  8. RelPartialLearnableDecoderLayer model · level 0 · unverified · 5014b04d3358c101
  9. sample_logits helper · level 0 · unverified · 582150577e5bd769
  10. MultiHeadAttn helper · level 1 · ran · e672e8a20905b62b
  11. PositionwiseFF helper · level 1 · ran · c96fba039a607703
  12. OptionalParameterList helper · level 0 · unverified · 55b4958b2a4e4373
  13. RelLearnableMultiHeadAttn model · level 0 · unverified · cb862dd19b1f381a
  14. RelPartialLearnableMultiHeadAttn model · level 0 · unverified · 5e1b71bde76b69e7
  15. RelMultiHeadAttn model · level 1 · ran · 8fa37260188b5fd8
  16. add_and_scale helper · level 1 · ran; the contract check could not run (RAISES) · 78d91efd74e4d12a

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 14 bricks; individually on a fixture: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

one of 18 siblings

  1. transformer_xl entry · level 0 · unverified · d077730400326171
  2. _cache_mem model · level 1 · ran; the contract check could not run (RAISES) · 9d5e914b24b8911a
  3. _create_mask helper · level 0 · unverified · c1f8a649a7a837d5
  4. embedding_lookup helper · level 0 · unverified · 5abf0267f0fc7514
  5. positionwise_ffn model · level 0 · unverified · ddf11fc956cd28ce
  6. rel_multihead_attn model · level 0 · unverified · 6ccb8d28491109b6
  7. relative_positional_encoding model · level 1 · ran · honoured contract · 8e76562720b0c921
  8. two_stream_rel_attn model · level 0 · unverified · 2d935f29546db9cd
  9. gelu helper · level 1 · ran · honoured contract · d08f324f950148de
  10. head_projection model · level 0 · unverified · 6804d62cb7cd8df3
  11. post_attention model · level 0 · unverified · cf208c8c20d52c1b
  12. rel_attn_core model · level 0 · unverified · b517847a8c809203
  13. positional_embedding helper · level 1 · ran; the contract check could not run (RAISES) · 9bf0f6e6298f3fbe
  14. rel_shift model · level 1 · ran; the contract check could not run (RAISES) · 5f7c5b38aeb29bf5

harvested Assembly for Transformer-XL (graph method: Transformer-XL). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 18 siblings

  1. RelativeMultiHeadAttention entry · level 0 · unverified · 274ae09f88dbb42a
  2. Linear helper · level 1 · ran · 1f215b06ae5d8476
  1. MemTransformerLM · 7e8e94db34a4c27b · 14 bricks; individually on a fixture: 9 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin
  2. TransformerModel · b2b2f8242acdc1d5 · 9 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  3. XLNet · e405f80080d3da6d · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  4. RelativeMultiHeadAttention · ed79e3501287d964 · 2 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  5. TransformerLayer · f7629f5167ba1e0d · 5 bricks; individually on a fixture: 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) · 2 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  6. MemTransformerLM · ff415c7b0c04a973 · 14 bricks; individually on a fixture: 8 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1901.02860") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ArticlesLanguage ModelingLanguage Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling Hutter Prize 24-layer Transformer-XL Bit per Character (BPC) 0.99 #4 of 18 Archive leaderboard report
Language Modelling Hutter Prize 24-layer Transformer-XL Number of params 277M #4 of 18 Archive leaderboard report
Language Modelling Hutter Prize 18-layer Transformer-XL Bit per Character (BPC) 1.03 #7 of 18 Archive leaderboard report
Language Modelling Hutter Prize 18-layer Transformer-XL Number of params 88M #7 of 18 Archive leaderboard report
Language Modelling Hutter Prize 12-layer Transformer-XL Bit per Character (BPC) 1.06 #9 of 18 Archive leaderboard report
Language Modelling Hutter Prize 12-layer Transformer-XL Number of params 41M #9 of 18 Archive leaderboard report
Language Modelling One Billion Word Transformer-XL Large Number of params 0.8B #4 of 27 Archive leaderboard report
Language Modelling One Billion Word Transformer-XL Large PPL 21.8 #4 of 27 Archive leaderboard report
Language Modelling One Billion Word Transformer-XL Base Number of params 0.46B #8 of 27 Archive leaderboard report
Language Modelling One Billion Word Transformer-XL Base PPL 23.5 #8 of 27 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) Transformer-XL Params 24M #22 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) Transformer-XL Test perplexity 54.55 #22 of 43 Archive leaderboard report
Language Modelling Penn Treebank (Word Level) Transformer-XL Validation perplexity 56.72 #22 of 43 Archive leaderboard report
Language Modelling Text8 Transformer-XL - 24 layers Bit per Character (BPC) 1.08 #5 of 24 Archive leaderboard report
Language Modelling Text8 Transformer-XL - 24 layers Number of params 277M #5 of 24 Archive leaderboard report
Language Modelling WikiText-103 Transformer-XL Large Number of params 257M #34 of 89 Archive leaderboard report
Language Modelling WikiText-103 Transformer-XL Large Test perplexity 18.3 #34 of 89 Archive leaderboard report
Language Modelling WikiText-103 Transformer-XL Large Validation perplexity 18.2 #34 of 89 Archive leaderboard report
Language Modelling WikiText-103 Transformer-XL Standard Number of params 151M #54 of 89 Archive leaderboard report
Language Modelling WikiText-103 Transformer-XL Standard Test perplexity 24.0 #54 of 89 Archive leaderboard report
Language Modelling WikiText-103 Transformer-XL Standard Validation perplexity 23.1 #54 of 89 Archive leaderboard report
Language Modelling enwik8 Transformer-XL (24 layers) Bit per Character (BPC) 0.99 #12 of 42 Archive leaderboard report
Language Modelling enwik8 Transformer-XL (24 layers) Number of params 277M #12 of 42 Archive leaderboard report
Language Modelling enwik8 Transformer-XL (18 layers) Bit per Character (BPC) 1.03 #23 of 42 Archive leaderboard report
Language Modelling enwik8 Transformer-XL (18 layers) Number of params 88M #23 of 42 Archive leaderboard report
Language Modelling enwik8 Transformer-XL (12 layers) Bit per Character (BPC) 1.06 #26 of 42 Archive leaderboard report
Language Modelling enwik8 Transformer-XL (12 layers) Number of params 41M #26 of 42 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

Introduced by this paper: Transformer-XL

AdamAdaptive Input RepresentationsAdaptive SoftmaxAttentionCosine AnnealingDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionReLUResidual ConnectionSoftmaxTransformer-XLVariational Dropout

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