{"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/the-impact-of-lora-on-the-emergence-of","title":"The Impact of LoRA on the Emergence of Clusters in Transformers","arxiv_id":"2402.15415","date":"2024-02-23","proceeding":null,"authors":["Hugo Koubbi","Matthieu Boussard","Louis Hernandez"],"abstract":"In this paper, we employ the mathematical framework on Transformers developed by \\citet{sander2022sinkformers,geshkovski2023emergence,geshkovski2023mathematical} to explore how variations in attention parameters and initial token values impact the structural dynamics of token clusters. Our analysis demonstrates that while the clusters within a modified attention matrix dynamics can exhibit significant divergence from the original over extended periods, they maintain close similarities over shorter intervals, depending on the parameter differences. This work contributes to the fine-tuning field through practical applications to the LoRA algorithm \\cite{hu2021lora,peft}, enhancing our understanding of the behavior of LoRA-enhanced Transformer models.","url_abs":"https://arxiv.org/abs/2402.15415v1","url_pdf":"https://arxiv.org/pdf/2402.15415v1.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":"the-impact-of-lora-on-the-emergence-of","repo_url":"https://github.com/HugoKoubbi/Transformers-2024-LoRA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"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":"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":{"syntology_url":"https://syntology.ai/paper/2402.15415","atlas_url":"https://app.syntology.ai/?focus=2402.15415","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.15415"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/HugoKoubbi/Transformers-2024-LoRA","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"ead8df8503bc811b","entry":"formatting_func","repo":"HugoKoubbi/Transformers-2024-LoRA","repo_kind":"official","path":"Llama2_Experiments/code/finetuning_llama2.py","file_url":"https://github.com/HugoKoubbi/Transformers-2024-LoRA/blob/HEAD/Llama2_Experiments/code/finetuning_llama2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ead8df8503bc811b"}},{"code_sha256_prefix":"713c3e4a1a9bfdd2","entry":"process_prompt","repo":"HugoKoubbi/Transformers-2024-LoRA","repo_kind":"official","path":"Llama2_Experiments/code/finetuning_llama2.py","file_url":"https://github.com/HugoKoubbi/Transformers-2024-LoRA/blob/HEAD/Llama2_Experiments/code/finetuning_llama2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"713c3e4a1a9bfdd2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}