{"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/gpt-neox-20b-an-open-source-autoregressive-1","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","arxiv_id":"2204.06745","date":"2022-04-14","proceeding":"BigScience (ACL) 2022 5","authors":["Sid Black","Stella Biderman","Eric Hallahan","Quentin Anthony","Leo Gao","Laurence Golding","Horace He","Connor Leahy","Kyle McDonell","Jason Phang","Michael Pieler","USVSN Sai Prashanth","Shivanshu Purohit","Laria Reynolds","Jonathan Tow","Ben Wang","Samuel Weinbach"],"abstract":"We introduce GPT-NeoX-20B, a 20 billion parameter autoregressive language model trained on the Pile, whose weights will be made freely and openly available to the public through a permissive license. It is, to the best of our knowledge, the largest dense autoregressive model that has publicly available weights at the time of submission. In this work, we describe \\model{}'s architecture and training and evaluate its performance on a range of language-understanding, mathematics, and knowledge-based tasks. We find that GPT-NeoX-20B is a particularly powerful few-shot reasoner and gains far more in performance when evaluated five-shot than similarly sized GPT-3 and FairSeq models. We open-source the training and evaluation code, as well as the model weights, at https://github.com/EleutherAI/gpt-neox.","url_abs":"https://arxiv.org/abs/2204.06745v1","url_pdf":"https://arxiv.org/pdf/2204.06745v1.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":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/eleutherai/gpt-neox","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/alon-albalak/online-data-mixing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/2023-MindSpore-1/ms-code-13/tree/main/GPT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/2023-MindSpore-1/ms-code-153","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/gpt_neox_japanese","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/gpt_neox_japanese","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/labmlai/neox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/gpt_neox_japanese","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-2/gpt_neox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"gpt-neox-20b-an-open-source-autoregressive-1","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-2/gpt_neox_japanese","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multi-task-language-understanding","task_name":"Multi-task Language Understanding"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"gpt-neo","method_name":"GPT-Neo"},{"method_slug":"gpt-neox","method_name":"GPT-NeoX"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"gpt-neox","name":"GPT-NeoX","full_name":"GPT-NeoX"}],"results":[{"leaderboard":"/sota/multi-task-language-understanding-on-mmlu","task":"Multi-task Language Understanding","dataset":"MML","model":"GPT-NeoX 20B (5-shot)","rank_in_archive_order":40,"of":44,"metrics":{"Average (%)":"33.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2204.06745","atlas_url":"https://app.syntology.ai/?focus=2204.06745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06745"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/2023-MindSpore-1/ms-code-13/tree/main/GPT","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/alon-albalak/online-data-mixing","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eleutherai/gpt-neox","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2023-MindSpore-1/ms-code-153","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/labmlai/neox","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/University/tree/main/model-2/gpt_neox","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/gpt_neox_japanese","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/gpt_neox_japanese","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-14/tree/main/gpt_neox_japanese","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/University/tree/main/model-2/gpt_neox_japanese","reach":null}],"summary":{"ran":2,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"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":"a154a97c7eecf3f9","entry":"infer","repo":"labmlai/neox","repo_kind":"listed","path":"src/neox/samples/generating_gpu.py","file_url":"https://github.com/labmlai/neox/blob/HEAD/src/neox/samples/generating_gpu.py","link_basis":"harvester_set","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":"a154a97c7eecf3f9"}},{"code_sha256_prefix":"7f6f91d6ca166416","entry":"infer","repo":"labmlai/neox","repo_kind":"listed","path":"src/neox/samples/generating_pipe.py","file_url":"https://github.com/labmlai/neox/blob/HEAD/src/neox/samples/generating_pipe.py","link_basis":"harvester_set","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":"7f6f91d6ca166416"}},{"code_sha256_prefix":"d3e001b86205c86a","entry":"infer","repo":"labmlai/neox","repo_kind":"listed","path":"src/neox/samples/generating_small_gpu.py","file_url":"https://github.com/labmlai/neox/blob/HEAD/src/neox/samples/generating_small_gpu.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":"d3e001b86205c86a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}