{"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/memorizing-transformers-1","title":"Memorizing Transformers","arxiv_id":"2203.08913","date":"2022-03-16","proceeding":"ICLR 2022 4","authors":["Yuhuai Wu","Markus N. Rabe","DeLesley Hutchins","Christian Szegedy"],"abstract":"Language models typically need to be trained or finetuned in order to acquire new knowledge, which involves updating their weights. We instead envision language models that can simply read and memorize new data at inference time, thus acquiring new knowledge immediately. In this work, we extend language models with the ability to memorize the internal representations of past inputs. We demonstrate that an approximate kNN lookup into a non-differentiable memory of recent (key, value) pairs improves language modeling across various benchmarks and tasks, including generic webtext (C4), math papers (arXiv), books (PG-19), code (Github), as well as formal theorems (Isabelle). We show that the performance steadily improves when we increase the size of memory up to 262K tokens. On benchmarks including code and mathematics, we find that the model is capable of making use of newly defined functions and theorems during test time.","url_abs":"https://arxiv.org/abs/2203.08913v1","url_pdf":"https://arxiv.org/pdf/2203.08913v1.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":"memorizing-transformers-1","repo_url":"https://github.com/lucidrains/memorizing-transformers-pytorch","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"memorizing-transformers-1","repo_url":"https://github.com/google-research/meliad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"memorizing-transformers-1","repo_url":"https://github.com/normal-computing/extended-mind-transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"memorizing-transformers-1","repo_url":"https://github.com/AIResearchHub/transformergallery","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"math","task_name":"Math"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.08913","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08913"}},"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/lucidrains/memorizing-transformers-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AIResearchHub/transformergallery","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google-research/meliad","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/normal-computing/extended-mind-transformers","reach":null}],"summary":{"ran":11,"ran_draft_wrong":2,"ran_fixture":3,"ran_honours":3,"ran_violates":1,"unverified":14},"by_repo_kind":{"official":{"samples":15,"ran":12,"repositories":1},"listed":{"samples":17,"ran":6,"repositories":3}},"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":"4673cf1999dcca6b","entry":"Attention","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4673cf1999dcca6b"}},{"code_sha256_prefix":"b2191b4a6430d0af","entry":"KNN","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2191b4a6430d0af"}},{"code_sha256_prefix":"2832f7cf743c7f86","entry":"KNNAttention","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2832f7cf743c7f86"}},{"code_sha256_prefix":"246054b031dda4de","entry":"KNNMemory","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"246054b031dda4de"}},{"code_sha256_prefix":"b90643346c166065","entry":"LlamaDynamicNTKScalingRotaryEmbedding","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b90643346c166065"}},{"code_sha256_prefix":"b704c9a5be0a15d7","entry":"LlamaLinearScalingRotaryEmbedding","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b704c9a5be0a15d7"}},{"code_sha256_prefix":"0765abcf04c608f6","entry":"LlamaMLP","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0765abcf04c608f6"}},{"code_sha256_prefix":"90915865fd797169","entry":"LlamaRMSNorm","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90915865fd797169"}},{"code_sha256_prefix":"580c588511c469d9","entry":"LlamaRotaryEmbedding","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"580c588511c469d9"}},{"code_sha256_prefix":"25d9116c53cb8eb2","entry":"PreNormResidual","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"25d9116c53cb8eb2"}},{"code_sha256_prefix":"9304ca35acfd717d","entry":"T5RelativePositionBias","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9304ca35acfd717d"}},{"code_sha256_prefix":"dd330ab84432cbc2","entry":"all_el_unique","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dd330ab84432cbc2"}},{"code_sha256_prefix":"49d79a24934a30e3","entry":"apply_rotary_pos_emb","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"49d79a24934a30e3"}},{"code_sha256_prefix":"76123fa16b69b8d4","entry":"cast_list","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76123fa16b69b8d4"}},{"code_sha256_prefix":"f70dcb896366697c","entry":"cast_tuple","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,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f70dcb896366697c"}},{"code_sha256_prefix":"1bdfb9459bbcd869","entry":"check_shape","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1bdfb9459bbcd869"}},{"code_sha256_prefix":"5844bf2b191c00ed","entry":"count_intersect","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5844bf2b191c00ed"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"f3232418205f7cbd","entry":"identity","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3232418205f7cbd"}},{"code_sha256_prefix":"2aa06e7db15eb39b","entry":"unique","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2aa06e7db15eb39b"}},{"code_sha256_prefix":"7fd92c090cad8a75","entry":"AttentionLayer","repo":"AIResearchHub/transformergallery","repo_kind":"listed","path":"transformer/memorizingtransformer.py","file_url":"https://github.com/AIResearchHub/transformergallery/blob/HEAD/transformer/memorizingtransformer.py","link_basis":"first_harvest_node","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":"7fd92c090cad8a75"}},{"code_sha256_prefix":"4039fb9f24228670","entry":"ExtendedLlamaAttention","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.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":"4039fb9f24228670"}},{"code_sha256_prefix":"a7a01f367b6da9da","entry":"ExtendedLlamaConfig","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.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":"a7a01f367b6da9da"}},{"code_sha256_prefix":"7419a094e9f98c3a","entry":"ExtendedLlamaDecoderLayer","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.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":"7419a094e9f98c3a"}},{"code_sha256_prefix":"ecccb74da133bd6a","entry":"ExtendedLlamaForCausalLM","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.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":"ecccb74da133bd6a"}},{"code_sha256_prefix":"29b4a33fabd0b32e","entry":"ExtendedLlamaModel","repo":"normal-computing/extended-mind-transformers","repo_kind":"listed","path":"src/llama/modeling.py","file_url":"https://github.com/normal-computing/extended-mind-transformers/blob/HEAD/src/llama/modeling.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":"29b4a33fabd0b32e"}},{"code_sha256_prefix":"3cb1714e61d5fad7","entry":"KNNMemoryList","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","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":"3cb1714e61d5fad7"}},{"code_sha256_prefix":"cbf31de811fec75e","entry":"MemorizingLayer","repo":"AIResearchHub/transformergallery","repo_kind":"listed","path":"transformer/memorizingtransformer.py","file_url":"https://github.com/AIResearchHub/transformergallery/blob/HEAD/transformer/memorizingtransformer.py","link_basis":"first_harvest_node","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":"cbf31de811fec75e"}},{"code_sha256_prefix":"c25e09cec3306193","entry":"MemorizingTransformer","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","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":"c25e09cec3306193"}},{"code_sha256_prefix":"c25efb685f36ecd3","entry":"MemorizingTransformer","repo":"AIResearchHub/transformergallery","repo_kind":"listed","path":"transformer/memorizingtransformer.py","file_url":"https://github.com/AIResearchHub/transformergallery/blob/HEAD/transformer/memorizingtransformer.py","link_basis":"first_harvest_node","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":"c25efb685f36ecd3"}},{"code_sha256_prefix":"d92db56afc61ab11","entry":"flatten_dict_string_keys","repo":"google-research/meliad","repo_kind":"listed","path":"model_info.py","file_url":"https://github.com/google-research/meliad/blob/HEAD/model_info.py","link_basis":"harvester_set","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":"d92db56afc61ab11"}},{"code_sha256_prefix":"7deb74a26342f2d3","entry":"initial_kvi","repo":"google-research/meliad","repo_kind":"listed","path":"transformer/attention.py","file_url":"https://github.com/google-research/meliad/blob/HEAD/transformer/attention.py","link_basis":"harvester_set","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":"7deb74a26342f2d3"}},{"code_sha256_prefix":"2ef0e2f355bf12a6","entry":"multi_context","repo":"lucidrains/memorizing-transformers-pytorch","repo_kind":"official","path":"memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","file_url":"https://github.com/lucidrains/memorizing-transformers-pytorch/blob/HEAD/memorizing_transformers_pytorch/memorizing_transformers_pytorch.py","link_basis":"first_harvest_node","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":"2ef0e2f355bf12a6"}},{"code_sha256_prefix":"1f2be62797cfccf1","entry":"should_run","repo":"google-research/meliad","repo_kind":"listed","path":"training_task.py","file_url":"https://github.com/google-research/meliad/blob/HEAD/training_task.py","link_basis":"harvester_set","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":"1f2be62797cfccf1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}