{"url":"/method/pangu-a","slug":"pangu-a","name":"PanGu-$α$","full_name":"PanGu-$α$","full_name_withheld":false,"description_markdown":"**PanGu-$α$** is an autoregressive language model (ALM) with up to 200 billion parameters pretrained on a large corpus of text, mostly in Chinese language. The architecture of PanGu-$α$ is based on Transformer, which has been extensively used as the backbone of a variety of pretrained language models such as [BERT](https://paperswithcode.com/method/bert) and [GPT](https://paperswithcode.com/method/gpt). Different from them, there's an additional query layer developed on top of Transformer layers which aims to explicitly induce the expected output.","description_state":"present","introduced_year":null,"introduced_by":{"title":"PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","paper":"/paper/pangu-a-large-scale-autoregressive-pretrained","first_author":"Wei Zeng","n_authors":38,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pangu-a-large-scale-autoregressive-pretrained"},"source":{"url":"https://arxiv.org/abs/2104.12369v1","title":"PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","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":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/pangu-a-large-scale-autoregressive-pretrained","title":"PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","date":"2021-04-26","arxiv_id":"2104.12369","n_code_links":5,"syntology":null}],"papers_shown":1,"tasks":[{"task":"/task/cloze-multi-choices-few-shot","name":"Cloze (multi-choices) (Few-Shot)","papers":1},{"task":"/task/cloze-multi-choices-one-shot","name":"Cloze (multi-choices) (One-Shot)","papers":1},{"task":"/task/cloze-multi-choices-zero-shot","name":"Cloze (multi-choices) (Zero-Shot)","papers":1},{"task":"/task/common-sense-reasoning-few-shot","name":"Common Sense Reasoning (Few-Shot)","papers":1},{"task":"/task/common-sense-reasoning-one-shot","name":"Common Sense Reasoning (One-Shot)","papers":1},{"task":"/task/common-sense-reasoning-zero-shot","name":"Common Sense Reasoning (Zero-Shot)","papers":1},{"task":"/task/dialogue-generation","name":"Dialogue Generation","papers":1},{"task":"/task/few-shot-image-classification","name":"Few-Shot Image Classification","papers":1},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":1},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":1},{"task":"/task/natural-language-inference-few-shot","name":"Natural Language Inference (Few-Shot)","papers":1},{"task":"/task/natural-language-inference-one-shot","name":"Natural Language Inference (One-Shot)","papers":1},{"task":"/task/natural-language-inference-zero-shot","name":"Natural Language Inference (Zero-Shot)","papers":1},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/reading-comprehension","name":"Reading Comprehension","papers":1},{"task":"/task/reading-comprehension-few-shot","name":"Reading Comprehension (Few-Shot)","papers":1},{"task":"/task/reading-comprehension-one-shot","name":"Reading Comprehension (One-Shot)","papers":1},{"task":"/task/reading-comprehension-zero-shot","name":"Reading Comprehension (Zero-Shot)","papers":1},{"task":"/task/text-classification","name":"Text Classification","papers":1}],"tasks_shown":20,"n_tasks":21,"usage_by_year":[{"year":"2021","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/pangu-a"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}