{"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/stack-more-layers-differently-high-rank","title":"ReLoRA: High-Rank Training Through Low-Rank Updates","arxiv_id":"2307.05695","date":"2023-07-11","proceeding":null,"authors":["Vladislav Lialin","Namrata Shivagunde","Sherin Muckatira","Anna Rumshisky"],"abstract":"Despite the dominance and effectiveness of scaling, resulting in large networks with hundreds of billions of parameters, the necessity to train overparameterized models remains poorly understood, while training costs grow exponentially. In this paper, we explore parameter-efficient training techniques as an approach to training large neural networks. We introduce a novel method called ReLoRA, which utilizes low-rank updates to train high-rank networks. We apply ReLoRA to training transformer language models with up to 1.3B parameters and demonstrate comparable performance to regular neural network training. ReLoRA saves up to 5.5Gb of RAM per GPU and improves training speed by 9-40% depending on the model size and hardware setup. Our findings show the potential of parameter-efficient techniques for large-scale pre-training.","url_abs":"https://arxiv.org/abs/2307.05695v4","url_pdf":"https://arxiv.org/pdf/2307.05695v4.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":"stack-more-layers-differently-high-rank","repo_url":"https://github.com/guitaricet/peft_pretraining","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"stack-more-layers-differently-high-rank","repo_url":"https://github.com/guitaricet/relora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"stack-more-layers-differently-high-rank","repo_url":"https://github.com/intel-analytics/BigDL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"stack-more-layers-differently-high-rank","repo_url":"https://github.com/intel/ipex-llm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2307.05695","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.05695"}},"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/guitaricet/peft_pretraining","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intel-analytics/BigDL","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/intel/ipex-llm","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/guitaricet/relora","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":2,"ran":4,"ran_draft_wrong":2,"unverified":6},"by_repo_kind":{"official":{"samples":14,"ran":8,"repositories":2}},"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":0,"samples":[{"code_sha256_prefix":"f725bc2d76076485","entry":"apply_rotary_pos_emb","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/modeling_llama.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f725bc2d76076485"}},{"code_sha256_prefix":"9b4dff79d5e6102c","entry":"apply_rotary_pos_emb","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/modeling_pythia.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/modeling_pythia.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9b4dff79d5e6102c"}},{"code_sha256_prefix":"4397f33726a2999e","entry":"attention_mask_func","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/modeling_pythia.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/modeling_pythia.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4397f33726a2999e"}},{"code_sha256_prefix":"f58a7fbb020fe7cd","entry":"get_cyclical_cosine_schedule_with_min_lr","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/training_utils.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/training_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f58a7fbb020fe7cd"}},{"code_sha256_prefix":"08daf3e9bcd8741a","entry":"get_scheculer","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/training_utils.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/training_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"08daf3e9bcd8741a"}},{"code_sha256_prefix":"d49462681436c44b","entry":"make_data_loader","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/megatron_dataset/dataloader.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/megatron_dataset/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d49462681436c44b"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/modeling_llama.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/modeling_llama.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"cb60aa6ee1172448","entry":"tokenize_and_chunk","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/dataloader.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/dataloader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cb60aa6ee1172448"}},{"code_sha256_prefix":"986b5739285a8cbf","entry":"check_args_torchrun_main","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/args_utils.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/args_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"986b5739285a8cbf"}},{"code_sha256_prefix":"6cd1023ec2204c22","entry":"evaluate_model","repo":"guitaricet/relora","repo_kind":"official","path":"torchrun_main.py","file_url":"https://github.com/guitaricet/relora/blob/HEAD/torchrun_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6cd1023ec2204c22"}},{"code_sha256_prefix":"a02bf1a7d404234a","entry":"infer_dataset_impl","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/megatron_dataset/indexed_dataset.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/megatron_dataset/indexed_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a02bf1a7d404234a"}},{"code_sha256_prefix":"8f615d9849c1a372","entry":"make_builder","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/megatron_dataset/indexed_dataset.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/megatron_dataset/indexed_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8f615d9849c1a372"}},{"code_sha256_prefix":"a4741eec9c94fa3c","entry":"make_dataset","repo":"guitaricet/peft_pretraining","repo_kind":"official","path":"peft_pretraining/megatron_dataset/indexed_dataset.py","file_url":"https://github.com/guitaricet/peft_pretraining/blob/HEAD/peft_pretraining/megatron_dataset/indexed_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a4741eec9c94fa3c"}},{"code_sha256_prefix":"72e11d65aa630194","entry":"parse_args","repo":"guitaricet/relora","repo_kind":"official","path":"pretokenize.py","file_url":"https://github.com/guitaricet/relora/blob/HEAD/pretokenize.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"72e11d65aa630194"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}