{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2VZ6H47AZEF4BAG52HKOLPWPCM","short_pith_number":"pith:2VZ6H47A","schema_version":"1.0","canonical_sha256":"d573e3f3e0c90bc080ddd1d4e5becf132c039cab3ec37c64f938e3691076264f","source":{"kind":"arxiv","id":"2407.02891","version":1},"attestation_state":"computed","paper":{"title":"GPTQT: Quantize Large Language Models Twice to Push the Efficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Qinyuan Ren, Yilin Lang, Yipin Guo","submitted_at":"2024-07-03T08:08:01Z","abstract_excerpt":"Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and enhance processing speed by expressing the weight of LLM in 3bit/2bit. Practice has shown that minimizing the quantization error of weights is ineffective, leading to overfitting. Therefore, GPTQT employs a progressive two-step approach: initially quantizing weights using Linear quantization to a relatively high bit, followed by converting obtained int weight to lower bit binary cod"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.02891","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-03T08:08:01Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"28234eeed24f03136ccaa53789941f26f531eecb4c9045b84aec33921041099e","abstract_canon_sha256":"367b94cf145d0cc374df32e49038faf90eeee9ec4a6e8a6204e7290a9367002a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:43.165347Z","signature_b64":"ZoGfGScNNyEoARXO47uRwQx4Vr9cmnmGVJov3OxnNvVJ8Wjg+d9nI2ERYRS/KWsF8Sc0SonJ044tJ4/Ik6XtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d573e3f3e0c90bc080ddd1d4e5becf132c039cab3ec37c64f938e3691076264f","last_reissued_at":"2026-07-05T08:39:43.164907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:43.164907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPTQT: Quantize Large Language Models Twice to Push the Efficiency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Qinyuan Ren, Yilin Lang, Yipin Guo","submitted_at":"2024-07-03T08:08:01Z","abstract_excerpt":"Due to their large size, generative Large Language Models (LLMs) require significant computing and storage resources. This paper introduces a new post-training quantization method, GPTQT, to reduce memory usage and enhance processing speed by expressing the weight of LLM in 3bit/2bit. Practice has shown that minimizing the quantization error of weights is ineffective, leading to overfitting. Therefore, GPTQT employs a progressive two-step approach: initially quantizing weights using Linear quantization to a relatively high bit, followed by converting obtained int weight to lower bit binary cod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02891","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.02891/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.02891","created_at":"2026-07-05T08:39:43.164970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02891v1","created_at":"2026-07-05T08:39:43.164970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02891","created_at":"2026-07-05T08:39:43.164970+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VZ6H47AZEF4","created_at":"2026-07-05T08:39:43.164970+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VZ6H47AZEF4BAG5","created_at":"2026-07-05T08:39:43.164970+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VZ6H47A","created_at":"2026-07-05T08:39:43.164970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2VZ6H47AZEF4BAG52HKOLPWPCM","json":"https://pith.science/pith/2VZ6H47AZEF4BAG52HKOLPWPCM.json","graph_json":"https://pith.science/api/pith-number/2VZ6H47AZEF4BAG52HKOLPWPCM/graph.json","events_json":"https://pith.science/api/pith-number/2VZ6H47AZEF4BAG52HKOLPWPCM/events.json","paper":"https://pith.science/paper/2VZ6H47A"},"agent_actions":{"view_html":"https://pith.science/pith/2VZ6H47AZEF4BAG52HKOLPWPCM","download_json":"https://pith.science/pith/2VZ6H47AZEF4BAG52HKOLPWPCM.json","view_paper":"https://pith.science/paper/2VZ6H47A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02891&json=true","fetch_graph":"https://pith.science/api/pith-number/2VZ6H47AZEF4BAG52HKOLPWPCM/graph.json","fetch_events":"https://pith.science/api/pith-number/2VZ6H47AZEF4BAG52HKOLPWPCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VZ6H47AZEF4BAG52HKOLPWPCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VZ6H47AZEF4BAG52HKOLPWPCM/action/storage_attestation","attest_author":"https://pith.science/pith/2VZ6H47AZEF4BAG52HKOLPWPCM/action/author_attestation","sign_citation":"https://pith.science/pith/2VZ6H47AZEF4BAG52HKOLPWPCM/action/citation_signature","submit_replication":"https://pith.science/pith/2VZ6H47AZEF4BAG52HKOLPWPCM/action/replication_record"}},"created_at":"2026-07-05T08:39:43.164970+00:00","updated_at":"2026-07-05T08:39:43.164970+00:00"}