{"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":"/method/gpt-neox","slug":"gpt-neox","name":"GPT-NeoX","full_name":"GPT-NeoX","full_name_withheld":false,"description_markdown":"**GPT-NeoX** is an autoregressive transformer decoder model whose architecture largely follows that of GPT-3, with a few notable deviations. The model has 20 billion parameters with 44 layers, a hidden dimension size of 6144, and 64 heads. The main difference with GPT-3 is the change in tokenizer, the addition of Rotary Positional Embeddings, the parallel computation of attention and feed-forward layers, and a different initialization scheme and hyperparameters.","description_state":"present","introduced_year":null,"introduced_by":{"title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","paper":"/paper/gpt-neox-20b-an-open-source-autoregressive-1","first_author":"Sid Black","n_authors":17,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/gpt-neox-20b-an-open-source-autoregressive-1"},"source":{"url":"https://arxiv.org/abs/2204.06745v1","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":11,"archive_num_papers":11,"papers_newest_first":[{"paper":"/paper/extending-llms-context-window-with-100","slug":"extending-llms-context-window-with-100","title":"Extending LLMs' Context Window with 100 Samples","date":"2024-01-13","arxiv_id":"2401.07004","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["gair-nlp/entropy-abf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-llm-inference-on-cpus","slug":"efficient-llm-inference-on-cpus","title":"Efficient LLM Inference on CPUs","date":"2023-11-01","arxiv_id":"2311.00502","n_code_links":2,"syntology":{"ran":2,"of":8,"n_ran_checked":0,"n_instrument":2,"unverified":6,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["intel/intel-extension-for-transformers"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/clex-continuous-length-extrapolation-for","slug":"clex-continuous-length-extrapolation-for","title":"CLEX: Continuous Length Extrapolation for Large Language Models","date":"2023-10-25","arxiv_id":"2310.16450","n_code_links":1,"syntology":{"ran":9,"of":10,"n_ran_checked":6,"n_instrument":3,"unverified":1,"pointer_only":1,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["damo-nlp-sg/clex"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":2,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-well-can-machine-generated-texts-be","title":"How well can machine-generated texts be identified and can language models be trained to avoid identification?","date":"2023-10-25","arxiv_id":"2310.16992","n_code_links":0,"syntology":null},{"paper":"/paper/h2o-heavy-hitter-oracle-for-efficient","slug":"h2o-heavy-hitter-oracle-for-efficient","title":"H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/struc-bench-are-large-language-models-really","slug":"struc-bench-are-large-language-models-really","title":"Struc-Bench: Are Large Language Models Really Good at Generating Complex Structured Data?","date":"2023-09-16","arxiv_id":"2309.08963","n_code_links":1,"syntology":null},{"paper":"/paper/h-2-o-heavy-hitter-oracle-for-efficient","slug":"h-2-o-heavy-hitter-oracle-for-efficient","title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","date":"2023-06-24","arxiv_id":"2306.14048","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["fminference/h2o"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/goat-fine-tuned-llama-outperforms-gpt-4-on","slug":"goat-fine-tuned-llama-outperforms-gpt-4-on","title":"Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks","date":"2023-05-23","arxiv_id":"2305.14201","n_code_links":1,"syntology":null},{"paper":"/paper/detectgpt-zero-shot-machine-generated-text","slug":"detectgpt-zero-shot-machine-generated-text","title":"DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature","date":"2023-01-26","arxiv_id":"2301.11305","n_code_links":4,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["eric-mitchell/detect-gpt"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/mass-editing-memory-in-a-transformer","slug":"mass-editing-memory-in-a-transformer","title":"Mass-Editing Memory in a Transformer","date":"2022-10-13","arxiv_id":"2210.07229","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":1,"n_instrument":5,"unverified":2,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","official":{"repos":["kmeng01/memit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/gpt-neox-20b-an-open-source-autoregressive-1","slug":"gpt-neox-20b-an-open-source-autoregressive-1","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","date":"2022-04-14","arxiv_id":"2204.06745","n_code_links":11,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["eleutherai/gpt-neox"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"papers_shown":11,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":11,"with_a_code_link":10,"where_syntology_ran_a_sample":7,"not_listed_spam_title":0,"listed":11,"listed_where_code_ran":7,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":6,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":6,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":7,"papers_where_code_ran_first_page":"/method/gpt-neox/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/gpt-neox/papers/ran/1","json":"/method/gpt-neox/papers/ran/1.json","rows":7}],"tasks":[{"task":"/task/language-modelling","name":"Language Modelling","papers":3},{"task":null,"name":"GPU","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":null,"name":"Position","papers":2},{"task":"/task/4k","name":"4k","papers":1},{"task":"/task/articles","name":"Articles","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/dataset-generation","name":"Dataset Generation","papers":1},{"task":"/task/hallucination","name":"Hallucination","papers":1},{"task":"/task/linguistic-acceptability","name":"Linguistic Acceptability","papers":1},{"task":"/task/multi-task-language-understanding","name":"Multi-task Language Understanding","papers":1},{"task":"/task/quantization","name":"Quantization","papers":1},{"task":"/task/text-detection","name":"Text Detection","papers":1},{"task":"/task/text-generation","name":"Text Generation","papers":1}],"tasks_shown":14,"n_tasks":14,"usage_by_year":[{"year":"2022","papers":2},{"year":"2023","papers":8},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/gpt-neox"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=GPT-NeoX","read_at":"2026-10-05T00:57:10+00:00","query":"GPT-NeoX","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2204.06745","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'GPT-NeoX' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":["GPT","GPT-D","H-GPT","RF-GPT","MS-GPT","GPT-RE","VA-GPT","GPT-ST"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"3db0c51ec6962b14ce40ae75696e0e6798529c03d96e42fcdb20647a9e1a70b7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}