{"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/can-we-scale-transformers-to-predict","title":"Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?","arxiv_id":"2303.04143","date":"2023-03-07","proceeding":null,"authors":["Boris Knyazev","Doha Hwang","Simon Lacoste-Julien"],"abstract":"Pretraining a neural network on a large dataset is becoming a cornerstone in machine learning that is within the reach of only a few communities with large-resources. We aim at an ambitious goal of democratizing pretraining. Towards that goal, we train and release a single neural network that can predict high quality ImageNet parameters of other neural networks. By using predicted parameters for initialization we are able to boost training of diverse ImageNet models available in PyTorch. When transferred to other datasets, models initialized with predicted parameters also converge faster and reach competitive final performance.","url_abs":"https://arxiv.org/abs/2303.04143v2","url_pdf":"https://arxiv.org/pdf/2303.04143v2.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":"can-we-scale-transformers-to-predict","repo_url":"https://github.com/samsungsailmontreal/ghn3","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"can-we-scale-transformers-to-predict","repo_url":"https://github.com/facebookresearch/ppuda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.04143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.04143"}},"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/facebookresearch/ppuda","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/samsungsailmontreal/ghn3","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":6,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"938b10bc0859efe4","entry":"avg_ddp_metric","repo":"samsungsailmontreal/ghn3","repo_kind":"official","path":"ghn3/ddp_utils.py","file_url":"https://github.com/samsungsailmontreal/ghn3/blob/HEAD/ghn3/ddp_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"938b10bc0859efe4"}},{"code_sha256_prefix":"9b2043b318b57ff4","entry":"create_light_modules","repo":"samsungsailmontreal/ghn3","repo_kind":"official","path":"ghn3/light_ops.py","file_url":"https://github.com/samsungsailmontreal/ghn3/blob/HEAD/ghn3/light_ops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b2043b318b57ff4"}},{"code_sha256_prefix":"01bd0a93297c2eb5","entry":"create_transformer","repo":"samsungsailmontreal/ghn3","repo_kind":"official","path":"ghn3/graphormer.py","file_url":"https://github.com/samsungsailmontreal/ghn3/blob/HEAD/ghn3/graphormer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01bd0a93297c2eb5"}},{"code_sha256_prefix":"c549f3ed10f17eeb","entry":"get_conv_name","repo":"samsungsailmontreal/ghn3","repo_kind":"official","path":"ghn3/graph.py","file_url":"https://github.com/samsungsailmontreal/ghn3/blob/HEAD/ghn3/graph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c549f3ed10f17eeb"}},{"code_sha256_prefix":"31d6226bb81368e0","entry":"get_metadata","repo":"samsungsailmontreal/ghn3","repo_kind":"official","path":"ghn3/nn.py","file_url":"https://github.com/samsungsailmontreal/ghn3/blob/HEAD/ghn3/nn.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31d6226bb81368e0"}},{"code_sha256_prefix":"51210ced01277bb6","entry":"ghn_parallel","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"51210ced01277bb6"}},{"code_sha256_prefix":"d520bc5e2c37efb8","entry":"transforms_imagenet","repo":"samsungsailmontreal/ghn3","repo_kind":"official","path":"ghn3/utils.py","file_url":"https://github.com/samsungsailmontreal/ghn3/blob/HEAD/ghn3/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d520bc5e2c37efb8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}