Home › Code › gelu_fast

gelu_fast

Syntologyentry name in harvested coderead from the graph 2026-09-24

gelu_fast appears in the code Syntology harvested for 39 papers, as 4 distinct code bodies found in 45 places (a place is one code body under one paper). At least one of them ran in 22 of the papers; 1 of the code bodies carries a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named gelu_fast do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 1 of the 4 distinct code bodies named gelu_fast; 3 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
1ran · our draft was wrong
0ran · fixture could not drive it
0ran
3unverified
1fingerprinted

Licence is a property of each copy, so it is counted per place: 25 of the 45 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

39 papers shown of 39, newest first; 45 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive; 2 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design 24 Oct 2024 VITA-Group/READ-ME/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified no licence file found · pointer only
Model Balancing Helps Low-data Training and Fine-tuning 16 Oct 2024 zihanghliu/modelbalancing/transformers/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified no licence file found · pointer only
Label Confidence Weighted Learning for Target-level Sentence Simplification 8 Oct 2024 astro-jon/LCWL/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted no licence file found · pointer only
Looped Transformers for Length Generalization 24 Sep 2024 UW-Madison-Lee-Lab/looped-tf/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified no licence file found · pointer only
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps 9 Jul 2024 voidism/lookback-lens/transformers-4.32.0/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified no licence file found · pointer only
Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning 1 Jul 2024 LINs-lab/CapaBoost/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 (permissive)
ESCoT: Towards Interpretable Emotional Support Dialogue Systems 16 Jun 2024 thu-coai/Emotional-Support-Conversation/codes/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted no licence file found · pointer only
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks 24 May 2024 leo-yangli/VB-LoRA/NLU/NLU/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted no licence file found · pointer only
Learning Syntax Without Planting Trees: Understanding When and Why Transformers Generalize Hierarchically 25 Apr 2024 kabirahuja2431/transformers-hg/transformers/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified no licence file found · pointer only
ScanTalk: 3D Talking Heads from Unregistered Scans 16 Mar 2024 miccunifi/ScanTalk/src/hubert/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted no licence file found · pointer only
Improving Open-Ended Text Generation via Adaptive Decoding 28 Feb 2024 zwhong714/adaptive_decoding/transformers-main/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified no licence file found · pointer only
Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning 22 Feb 2024 johnathan-xie/sma/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 (permissive)
Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models 4 Feb 2024 identical code first harvested elsewhere a4475703ff58ecf9 ran · our draft was wrong fingerprinted licence of this copy not recorded
Generative Dense Retrieval: Memory Can Be a Burden 19 Jan 2024 ypw0102/gdr/GDR_model/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted no licence file found · pointer only
Mask Grounding for Referring Image Segmentation 19 Dec 2023 yxchng/mask-grounding/bert/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted AGPL-3.0 (copyleft) · pointer only
An Analysis and Mitigation of the Reversal Curse 13 Nov 2023 trestad/mitigating-reversal-curse/transformers/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified no licence file found · pointer only
Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding 12 Nov 2023 alibaba/EasyNLP/easynlp/modelzoo/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
NOLA: Compressing LoRA using Linear Combination of Random Basis 4 Oct 2023 UCDvision/NOLA/gpt/examples/NLG/src/model_nola.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted MIT (permissive)
Learning to Predict Concept Ordering for Common Sense Generation 12 Sep 2023 tianhuizhang/concept_ordering/bart/src/model/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted no licence file found · pointer only
Contrastive Grouping with Transformer for Referring Image Segmentation 2 Sep 2023 toneyaya/cgformer/bert/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted MIT (permissive)
Token-wise Decomposition of Autoregressive Language Model Hidden States for Analyzing Model Predictions 17 May 2023 byungdoh/llm_decomposition/huggingface/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 (permissive)
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning 28 Jan 2023 cambridgeltl/autopeft/adapter-transformers-adapters3.1.0/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisal 21 Dec 2022 byungdoh/attn_dist/huggingface/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 (permissive)
AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization 2 Dec 2022 bhargaviparanjape/robust-transformers/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
EvEntS ReaLM: Event Reasoning of Entity States via Language Models 10 Nov 2022 spilioeve/eventsrealm/transformers-single-all-attribute-prompt-experiments/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified MIT (permissive)
Locally Typical Sampling 1 Feb 2022 cimeister/typical-sampling/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only
Locally Typical Sampling 1 Feb 2022 cimeister/typical-sampling/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
Attention Approximates Sparse Distributed Memory 10 Nov 2021 trentbrick/attention-approximates-sdm/HugFace/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted MIT (permissive)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models 30 Oct 2021 vita-group/dsee/non-GPT-2/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted MIT (permissive)
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models 30 Oct 2021 vita-group/dsee/non-GPT-2/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified MIT (permissive)
Towards a Unified View of Parameter-Efficient Transfer Learning 8 Oct 2021 jxhe/unify-parameter-efficient-tuning/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only
Towards a Unified View of Parameter-Efficient Transfer Learning 8 Oct 2021 jxhe/unify-parameter-efficient-tuning/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation 8 Sep 2021 UKPLab/m-AMR2Text/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation 8 Sep 2021 UKPLab/m-AMR2Text/transformers/activations_tf.py ac1bc5cb23b3f2ec unverified Apache-2.0 (permissive)
Learned Token Pruning for Transformers 2 Jul 2021 kssteven418/ltp/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only
Learned Token Pruning for Transformers 2 Jul 2021 kssteven418/ltp/src/transformers/activations_tf.py ac1bc5cb23b3f2ec unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
X-FACT: A New Benchmark Dataset for Multilingual Fact Checking 17 Jun 2021 utahnlp/x-fact/transformers/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted MIT (permissive)
Dialogue-oriented Pre-training 1 Jun 2021 xyease/Dialog-PrLM/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphs 16 Apr 2021 GT-SALT/Structure-Aware-BART/transformers/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted MIT (permissive)
Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models 16 Apr 2021 alab-nii/eval_vl_glue/eval_vl_glue/transformers_volta/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
Transformers for Modeling Physical Systems 4 Oct 2020 zabaras/transformer-physx/trphysx/transformer/utils.py b253e96edee87a52 unverified MIT (permissive)
AdapterHub: A Framework for Adapting Transformers 15 Jul 2020 adapter-hub/adapter-transformers-legacy/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 recorded; this copy not marked cleared · pointer only
arXiv:2024.findings-naacl.117 qqplot/dcpmi/transformers/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified MIT (permissive)
arXiv:2022.naacl-main.130 parovicm/BADX/src/transformers/activations.py a4475703ff58ecf9 ran · our draft was wrong fingerprinted Apache-2.0 (permissive)
arXiv:2022.naacl-main.130 parovicm/BADX/src/transformers/activations_tf.py 37a5eed2dbd663ca unverified Apache-2.0 recorded; this copy not marked cleared · pointer only

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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