{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/gift-sw-gaussian-noise-injected-fine-tuning","title":"GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs","arxiv_id":"2408.15300","date":"2024-08-27","proceeding":null,"authors":["Maxim Zhelnin","Viktor Moskvoretskii","Egor Shvetsov","Egor Venediktov","Mariya Krylova","Aleksandr Zuev","Evgeny Burnaev"],"abstract":"Parameter Efficient Fine-Tuning (PEFT) methods have gained popularity and democratized the usage of Large Language Models (LLMs). Recent studies have shown that a small subset of weights significantly impacts performance. Based on this observation, we introduce a novel PEFT method, called Gaussian noise Injected Fine Tuning of Salient Weights (GIFT-SW). Our method updates only salient columns, while injecting Gaussian noise into non-salient ones. To identify these columns, we developeda generalized sensitivity metric that extends and unifies metrics from previous studies. Experiments with LLaMA models demonstrate that GIFT-SW outperforms full fine-tuning and modern PEFT methods under the same computational budget. Moreover, GIFT-SW offers practical advantages to recover performance of models subjected to mixed-precision quantization with keeping salient weights in full precision.","url_abs":"https://arxiv.org/abs/2408.15300v1","url_pdf":"https://arxiv.org/pdf/2408.15300v1.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":"gift-sw-gaussian-noise-injected-fine-tuning","repo_url":"https://github.com/On-Point-RND/GIFT_SW","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"parameter-efficient-fine-tuning","task_name":"parameter-efficient fine-tuning"}],"methods":[{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-boolq","task":"parameter-efficient fine-tuning","dataset":"BoolQ","model":"LLaMA2-7b","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy (% )":"82.63"},"uses_additional_data":false},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-hellaswag","task":"parameter-efficient fine-tuning","dataset":"HellaSwag","model":"LLaMA2-7b","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy (% )":"76.68"},"uses_additional_data":true},{"leaderboard":"/sota/parameter-efficient-fine-tuning-on-winogrande","task":"parameter-efficient fine-tuning","dataset":"WinoGrande","model":"LLaMA2-7b","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy (% )":"70.80"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2408.15300","atlas_url":"https://app.syntology.ai/?focus=2408.15300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15300"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2408.15300"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2408.15300"},"call":"get_harvested_code_for_paper(arxiv_id=\"2408.15300\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2408.15300"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2408.15300\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2408.15300"},"call":"get_concepts_for_paper(arxiv_id=\"2408.15300\")"}],"by_repo":[{"repo":"On-Point-RND/GIFT_SW","kind":"official","samples":2,"ran":2,"instrument":2,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2408.15300.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2408.15300.svg"},"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/On-Point-RND/GIFT_SW","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_honours":2,"ran_fixture":2,"ran_draft_wrong":1},"n_samples":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":2,"ran":2,"n_ran_checked":0,"n_instrument":2,"repositories":1},"unlocated":{"samples":3,"ran":3,"n_ran_checked":2,"n_instrument":1,"repositories":0,"is":"identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded"}},"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":5,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":2,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"32380a050ca033d4","code_sha256_prefix":"32380a050ca033d4","entry":"b2mb","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"x:int/0/int","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"32380a050ca033d4"},"code_page":"/code/b2mb","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"32380a050ca033d4"}},{"code_sha256":"6a1220317ec3675f","code_sha256_prefix":"6a1220317ec3675f","entry":"check_if_peft_model","repo":"On-Point-RND/GIFT_SW","repo_kind":"official","path":"src/peft/helpers.py","file_url":"https://github.com/On-Point-RND/GIFT_SW/blob/HEAD/src/peft/helpers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model_name_or_path:str/0/str","fixture_out_type":"bool","level_recorded_at":"2026-09-25T15:42:09.353852+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from juyongjiang/KaSA, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"6a1220317ec3675f"}},{"code_sha256":"bdad3d08a6241ede","code_sha256_prefix":"bdad3d08a6241ede","entry":"get_closest_label","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"signature":"eval_pred:str/0/str, classes:list/1/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":"/code/get-closest-label","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"bdad3d08a6241ede"}},{"code_sha256":"a3daaf3e5bdfc709","code_sha256_prefix":"a3daaf3e5bdfc709","entry":"is_torch_tpu_available","repo":"On-Point-RND/GIFT_SW","repo_kind":"official","path":"src/peft/import_utils.py","file_url":"https://github.com/On-Point-RND/GIFT_SW/blob/HEAD/src/peft/import_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"check_device:bool/0/bool","fixture_out_type":"bool","level_recorded_at":"2026-09-25T23:22:42.264232+00:00","code_page":"/code/is-torch-tpu-available","census":null,"licence":"Apache-2.0","inline_ok":false,"inline_ok_link":true,"withheld_clause":"this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from juyongjiang/KaSA, and GitHub detected no licence in that repository when it was checked","mcp_get_code":{"code_sha256":"a3daaf3e5bdfc709"}},{"code_sha256":"d267d33e45b87bcd","code_sha256_prefix":"d267d33e45b87bcd","entry":"levenshtein_distance","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"signature":"str1:str/0/str, str2:str/0/str","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"d267d33e45b87bcd"},"code_page":"/code/levenshtein-distance","census":null,"licence":null,"inline_ok":false,"inline_ok_link":false,"withheld_clause":"this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it","mcp_get_code":{"code_sha256":"d267d33e45b87bcd"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a3942e4923a9c622878d725783dee4f9bf8289e64a3fe2e463884be6967a001f","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}