Papers › RoFormer: Enhanced Transformer with Rotary Position Embedding

RoFormer: Enhanced Transformer with Rotary Position Embedding

20 Apr 2021arXiv:2104.09864archive 2025-07-28

Jianlin Su, Yu Lu, Shengfeng Pan, Ahmed Murtadha, Bo Wen, Yunfeng Liu

Position encoding recently has shown effective in the transformer architecture. It enables valuable supervision for dependency modeling between elements at different positions of the sequence. In this paper, we first investigate various methods to integrate positional information into the learning process of transformer-based language models. Then, we propose a novel method named Rotary Position Embedding(RoPE) to effectively leverage the positional information. Specifically, the proposed RoPE encodes the absolute position with a rotation matrix and meanwhile incorporates the explicit relative position dependency in self-attention formulation. Notably, RoPE enables valuable properties, including the flexibility of sequence length, decaying inter-token dependency with increasing relative distances, and the capability of equipping the linear self-attention with relative position encoding. Finally, we evaluate the enhanced transformer with rotary position embedding, also called RoFormer, on various long text classification benchmark datasets. Our experiments show that it consistently overcomes its alternatives. Furthermore, we provide a theoretical analysis to explain some experimental results. RoFormer is already integrated into Huggingface: \url{https://huggingface.co/docs/transformers/model_doc/roformer}.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2104.09864")

Code

Syntology Ran 14 of 16 code samples harvested from 10 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 5 ran · our draft was wrong; 1 ran · fixture could not drive it; 7 ran with no contract checked.

By repository: community (archive-listed): 16 samples from 10 repositories, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

ZhuiyiTechnology/roformer officialmentioned in papertfApache-2.0 report
airi-institute/gena_lm mentioned on GitHubpytorch report
baichuan-inc/baichuan-13b mentioned on GitHubpytorchApache-2.0 report
baichuan-inc/baichuan-7b mentioned on GitHubpytorch report
bangoc123/rope-visualization mentioned on GitHub report
databrickslabs/dolly mentioned on GitHubpytorch report
ezelikman/STaR mentioned on GitHubjax report
huggingface/transformers mentioned on GitHubpytorch report
kakaobrain/kogpt mentioned on GitHubpytorch report
kingoflolz/mesh-transformer-jax mentioned on GitHubjax report
lucidrains/reformer-pytorch mentioned on GitHubpytorch report
lucidrains/rotary-embedding-torch mentioned on GitHubpytorch report
singaln/Roformer_Simlarity mentioned on GitHubpytorch report
varungumma/fairseq mentioned on GitHubpytorch report
willGuimont/transformers mentioned on GitHubpytorch 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.

Code Syntology ran Syntology

16 samples harvested; 14 ran; 1 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · honoured contract
5ran · our draft was wrong
1ran · fixture could not drive it
7ran
2unverified

Licence: 0 of the 16 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 10 repositories linked to this paper, official or community; each sample names its own and says which. “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. “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.

Each sample ends with its 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.

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 from a repository marked official are listed first. 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 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

MultiHeadsAttention singaln/Roformer_Simlarity/Rotransformer.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · ec6ef1c866e39c6f · report
RoPE labmlai/annotated_deep_learning_paper_implementations/labml_nn/neox/model.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · 8f063cad604c5b86 · report
RotaryEmbedding AryaAftab/rotary-embedding-tensorflow/rotary_embedding_tensorflow/rotary_embedding_tensorflow.py community (archive-listed) ran MIT (permissive) · 0fe09c685e79fefc · report
RotaryEmbedding varungumma/fairseq/fairseq/modules/rotary_embedding.py community (archive-listed) ran · metamorphic tier: deterministic MIT (permissive) · dbb6d6a0d27a25f4 · report
RotaryEmbedding airi-institute/gena_lm/src/gena_lm/modeling_bert.py community (archive-listed) ran MIT (permissive) · 9a156a004cf5913c · report
RotaryEmbedding lucidrains/rotary-embedding-torch/rotary_embedding_torch/rotary_embedding_torch.py community (archive-listed) ran fingerprinted MIT (permissive) · 0a4292dfdf0c449d · report
RotaryEmbedding baichuan-inc/baichuan-7b/models/modeling_baichuan.py community (archive-listed) ran Apache-2.0 (permissive) · d05c5eb6cdfb5b97 · report
apply_rotary_emb varungumma/fairseq/fairseq/modules/rotary_embedding.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 60f6b43d9fa0bb55 · report
apply_rotary_emb lucidrains/rotary-embedding-torch/rotary_embedding_torch/rotary_embedding_torch.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 0a495c8bcfb0380b · report
apply_rotary_pos_emb lucidrains/reformer-pytorch/reformer_pytorch/reformer_pytorch.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 3c0f5df83f530eba · report
relative_positional_encoding willGuimont/transformers/nnet/positional_encoding/relative_positional_encoding.py community (archive-listed) ran · honoured contract MIT (permissive) · e37b416bd6989338 · report
repeat AryaAftab/rotary-embedding-tensorflow/rotary_embedding_tensorflow/rotary_embedding_tensorflow.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 4c8c38feed7983ab · report
rotate_half varungumma/fairseq/fairseq/modules/rotary_embedding.py community (archive-listed) ran · our draft was wrong fingerprinted MIT (permissive) · 58823d9435a8751b · report
slice_at_dim lucidrains/rotary-embedding-torch/rotary_embedding_torch/rotary_embedding_torch.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 50c38f60f1badef7 · report
RelativePositionalEncoding willGuimont/transformers/nnet/positional_encoding/relative_positional_encoding.py community (archive-listed) unverified MIT (permissive) · c4c1375689d7d3dc · report
RoFormerSelfAttention JunnYu/RoFormer_pytorch/src/roformer/modeling_roformer.py community (archive-listed) unverified Apache-2.0 (permissive) · 5e8d748cacb045bd · report

Tasks

Semantic Text MatchingText Classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Rotary Embeddings

Rotary Embeddings

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