{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P2FOV5Q5TCLL5Q5D6U4HM334L4","short_pith_number":"pith:P2FOV5Q5","schema_version":"1.0","canonical_sha256":"7e8aeaf61d9896bec3a3f538766f7c5f253d00a88ba3f8d5ae3c1654f7e7f065","source":{"kind":"arxiv","id":"2402.13533","version":1},"attestation_state":"computed","paper":{"title":"FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DC"],"primary_cat":"cs.LG","authors_text":"Anwar Walid, Guoxuan Wang, Jie Zhang, Weiqing Tong, Xiao-Yang Liu","submitted_at":"2024-02-21T05:03:17Z","abstract_excerpt":"Large language models (LLMs) are computationally intensive. The computation workload and the memory footprint grow quadratically with the dimension (layer width). Most of LLMs' parameters come from the linear layers of the transformer structure and are highly redundant. These linear layers contribute more than 80% of the computation workload and 99% of the model size. To pretrain and finetune LLMs efficiently, there are three major challenges to address: 1) reducing redundancy of the linear layers; 2) reducing GPU memory footprint; 3) improving GPU utilization when using distributed training. "},"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":"2402.13533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-21T05:03:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DC"],"title_canon_sha256":"da2c1c5ac51627079a916b6d424e77a7d816a05808f64b3e0f908b3928278b51","abstract_canon_sha256":"6efbb5c220fddf9e08cc7406a84ebf1e4bcaf329cb39cb39838eee1299372a0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:33.825080Z","signature_b64":"pQOyHIdhzcl+y9f2L/yahcRqZxu4w5HjB0C+91rk531R03SHcvPpqeoYUvvWxgnh2vdG2rYpAtOQQWerm6hKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e8aeaf61d9896bec3a3f538766f7c5f253d00a88ba3f8d5ae3c1654f7e7f065","last_reissued_at":"2026-07-05T07:47:33.824602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:33.824602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinGPT-HPC: Efficient Pretraining and Finetuning Large Language Models for Financial Applications with High-Performance Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DC"],"primary_cat":"cs.LG","authors_text":"Anwar Walid, Guoxuan Wang, Jie Zhang, Weiqing Tong, Xiao-Yang Liu","submitted_at":"2024-02-21T05:03:17Z","abstract_excerpt":"Large language models (LLMs) are computationally intensive. The computation workload and the memory footprint grow quadratically with the dimension (layer width). Most of LLMs' parameters come from the linear layers of the transformer structure and are highly redundant. These linear layers contribute more than 80% of the computation workload and 99% of the model size. To pretrain and finetune LLMs efficiently, there are three major challenges to address: 1) reducing redundancy of the linear layers; 2) reducing GPU memory footprint; 3) improving GPU utilization when using distributed training. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13533","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/2402.13533/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":"2402.13533","created_at":"2026-07-05T07:47:33.824664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13533v1","created_at":"2026-07-05T07:47:33.824664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13533","created_at":"2026-07-05T07:47:33.824664+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2FOV5Q5TCLL","created_at":"2026-07-05T07:47:33.824664+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2FOV5Q5TCLL5Q5D","created_at":"2026-07-05T07:47:33.824664+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2FOV5Q5","created_at":"2026-07-05T07:47:33.824664+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/P2FOV5Q5TCLL5Q5D6U4HM334L4","json":"https://pith.science/pith/P2FOV5Q5TCLL5Q5D6U4HM334L4.json","graph_json":"https://pith.science/api/pith-number/P2FOV5Q5TCLL5Q5D6U4HM334L4/graph.json","events_json":"https://pith.science/api/pith-number/P2FOV5Q5TCLL5Q5D6U4HM334L4/events.json","paper":"https://pith.science/paper/P2FOV5Q5"},"agent_actions":{"view_html":"https://pith.science/pith/P2FOV5Q5TCLL5Q5D6U4HM334L4","download_json":"https://pith.science/pith/P2FOV5Q5TCLL5Q5D6U4HM334L4.json","view_paper":"https://pith.science/paper/P2FOV5Q5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13533&json=true","fetch_graph":"https://pith.science/api/pith-number/P2FOV5Q5TCLL5Q5D6U4HM334L4/graph.json","fetch_events":"https://pith.science/api/pith-number/P2FOV5Q5TCLL5Q5D6U4HM334L4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2FOV5Q5TCLL5Q5D6U4HM334L4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2FOV5Q5TCLL5Q5D6U4HM334L4/action/storage_attestation","attest_author":"https://pith.science/pith/P2FOV5Q5TCLL5Q5D6U4HM334L4/action/author_attestation","sign_citation":"https://pith.science/pith/P2FOV5Q5TCLL5Q5D6U4HM334L4/action/citation_signature","submit_replication":"https://pith.science/pith/P2FOV5Q5TCLL5Q5D6U4HM334L4/action/replication_record"}},"created_at":"2026-07-05T07:47:33.824664+00:00","updated_at":"2026-07-05T07:47:33.824664+00:00"}