{"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/transformers-are-multi-state-rnns","title":"Transformers are Multi-State RNNs","arxiv_id":"2401.06104","date":"2024-01-11","proceeding":null,"authors":["Matanel Oren","Michael Hassid","Nir Yarden","Yossi Adi","Roy Schwartz"],"abstract":"Transformers are considered conceptually different from the previous generation of state-of-the-art NLP models - recurrent neural networks (RNNs). In this work, we demonstrate that decoder-only transformers can in fact be conceptualized as unbounded multi-state RNNs - an RNN variant with unlimited hidden state size. We further show that transformers can be converted into $\\textit{bounded}$ multi-state RNNs by fixing the size of their hidden state, effectively compressing their key-value cache. We introduce a novel, training-free compression policy - $\\textbf{T}$oken $\\textbf{O}$mission $\\textbf{V}$ia $\\textbf{A}$ttention (TOVA). Our experiments with four long range tasks and several LLMs show that TOVA outperforms several baseline compression policies. Particularly, our results are nearly on par with the full model, using in some cases only $\\frac{1}{8}$ of the original cache size, which translates to 4.8X higher throughput. Our results shed light on the connection between transformers and RNNs, and help mitigate one of LLMs' most painful computational bottlenecks - the size of their key-value cache. We publicly release our code at https://github.com/schwartz-lab-NLP/TOVA","url_abs":"https://arxiv.org/abs/2401.06104v2","url_pdf":"https://arxiv.org/pdf/2401.06104v2.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":"transformers-are-multi-state-rnns","repo_url":"https://github.com/schwartz-lab-nlp/tova","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.06104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.06104"}},"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/schwartz-lab-nlp/tova","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/schwartz-lab-NLP/TOVA","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"54de72995b87c580","entry":"tova_llama_attention_forward","repo":"schwartz-lab-NLP/TOVA","repo_kind":"official","path":"src/convert_models/llama_custom.py","file_url":"https://github.com/schwartz-lab-NLP/TOVA/blob/HEAD/src/convert_models/llama_custom.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":"54de72995b87c580"}},{"code_sha256_prefix":"f6c0299a5cc213e4","entry":"tova_llama_prepare_inputs_for_generation_generation","repo":"schwartz-lab-nlp/tova","repo_kind":"official","path":"src/convert_models/llama_custom.py","file_url":"https://github.com/schwartz-lab-nlp/tova/blob/HEAD/src/convert_models/llama_custom.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":"f6c0299a5cc213e4"}},{"code_sha256_prefix":"a1ffc30c1fe8ddd4","entry":"tova_mistral_attention_forward","repo":"schwartz-lab-nlp/tova","repo_kind":"official","path":"src/convert_models/mistral_custom.py","file_url":"https://github.com/schwartz-lab-nlp/tova/blob/HEAD/src/convert_models/mistral_custom.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":"a1ffc30c1fe8ddd4"}},{"code_sha256_prefix":"756d1d52f23e0c15","entry":"tova_mistral_prepare_inputs_for_generation_generation","repo":"schwartz-lab-nlp/tova","repo_kind":"official","path":"src/convert_models/mistral_custom.py","file_url":"https://github.com/schwartz-lab-nlp/tova/blob/HEAD/src/convert_models/mistral_custom.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":"756d1d52f23e0c15"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}