{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dijiang-efficient-large-language-models","title":"DiJiang: Efficient Large Language Models through Compact Kernelization","arxiv_id":"2403.19928","date":"2024-03-29","proceeding":null,"authors":["Hanting Chen","Zhicheng Liu","Xutao Wang","Yuchuan Tian","Yunhe Wang"],"abstract":"In an effort to reduce the computational load of Transformers, research on linear attention has gained significant momentum. However, the improvement strategies for attention mechanisms typically necessitate extensive retraining, which is impractical for large language models with a vast array of parameters. In this paper, we present DiJiang, a novel Frequency Domain Kernelization approach that enables the transformation of a pre-trained vanilla Transformer into a linear complexity model with little training costs. By employing a weighted Quasi-Monte Carlo method for sampling, the proposed approach theoretically offers superior approximation efficiency. To further reduce the training computational complexity, our kernelization is based on Discrete Cosine Transform (DCT) operations. Extensive experiments demonstrate that the proposed method achieves comparable performance to the original Transformer, but with significantly reduced training costs and much faster inference speeds. Our DiJiang-7B achieves comparable performance with LLaMA2-7B on various benchmark while requires only about 1/50 training cost. Code is available at https://github.com/YuchuanTian/DiJiang.","url_abs":"https://arxiv.org/abs/2403.19928v2","url_pdf":"https://arxiv.org/pdf/2403.19928v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dijiang-efficient-large-language-models","repo_url":"https://github.com/yuchuantian/dijiang","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discrete-cosine-transform","method_name":"Discrete Cosine Transform"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.19928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.19928"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yuchuantian/dijiang","reach":{"status":"ok"}}],"summary":{"ran_fixture":2,"ran":3,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":6,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"8a38d7c525fad8f1","entry":"accuracy","repo":"yuchuantian/dijiang","repo_kind":"official","path":"train_pythia.py","file_url":"https://github.com/yuchuantian/dijiang/blob/HEAD/train_pythia.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8a38d7c525fad8f1"}},{"code_sha256_prefix":"d61c483a3c2b3156","entry":"apply_rotary_pos_emb","repo":"yuchuantian/dijiang","repo_kind":"official","path":"modeling/pythia-160M-dijiang/modeling_gpt_neox_dijiang.py","file_url":"https://github.com/yuchuantian/dijiang/blob/HEAD/modeling/pythia-160M-dijiang/modeling_gpt_neox_dijiang.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d61c483a3c2b3156"}},{"code_sha256_prefix":"4397f33726a2999e","entry":"attention_mask_func","repo":"yuchuantian/dijiang","repo_kind":"official","path":"modeling/pythia-160M-dijiang/modeling_gpt_neox_dijiang.py","file_url":"https://github.com/yuchuantian/dijiang/blob/HEAD/modeling/pythia-160M-dijiang/modeling_gpt_neox_dijiang.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4397f33726a2999e"}},{"code_sha256_prefix":"095a8b81ca7acd65","entry":"compute_acc","repo":"yuchuantian/dijiang","repo_kind":"official","path":"train_pythia.py","file_url":"https://github.com/yuchuantian/dijiang/blob/HEAD/train_pythia.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"095a8b81ca7acd65"}},{"code_sha256_prefix":"44b82bf0bb0e8bc1","entry":"compute_ppl","repo":"yuchuantian/dijiang","repo_kind":"official","path":"train_pythia.py","file_url":"https://github.com/yuchuantian/dijiang/blob/HEAD/train_pythia.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44b82bf0bb0e8bc1"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"yuchuantian/dijiang","repo_kind":"official","path":"modeling/pythia-160M-dijiang/modeling_gpt_neox_dijiang.py","file_url":"https://github.com/yuchuantian/dijiang/blob/HEAD/modeling/pythia-160M-dijiang/modeling_gpt_neox_dijiang.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}