Yi-Lightning Technical Report
Technical report on the Yi-Lightning model by 01.AI; arXiv 2412.01253, version 1 of 2 December 2024 cited.
- Issued by
- 01.AI
- Authors credited
- No authorship claim recorded yet. The source records list 01.AI.
- Dates
- Published 2024-12-02 issue evidence
- Exact source
- Yi-Lightning Technical Report (arXiv abstract page, v1) arXiv · published 2024-12-02 · Dated document, retrieved on 2026-10-29 (SHA-256 da13a49af5e9c1cfa5352a4e199812ab45fd66e89ea0a2ed5674b07431bd1775) directly from the publisher. Version: 2412.01253v1. Abstract page of version 1 (submitted 2 December 2024); the page lists later versions v2 to v5 (3 December 2024 to 22 January 2025), not inspected.
- Yi-Lightning Technical Report (arXiv PDF, v1) arXiv · published 2024-12-02 · Dated document, retrieved on 2026-10-29 (SHA-256 1a78807735c4c06f48ba40376dd7fae3241a2c6beab6c5a2f5d2750eaa5f050a) directly from the publisher. Version: 2412.01253v1. PDF of version 1; later versions not inspected.
Appears in
No collection holds a record about this document yet.
Versions
No other versions of this document are recorded. The evidence applies to the source version listed above. Other versions, such as a preprint, working paper or journal publication, are not identified or substituted.
Issue and authorship records
Documentary relations
Each relation is listed separately. Citing, crediting and reporting the use of a method are different acts, and none of them shows agreement or influence by itself.
Not recorded for this document: cites · cited by · explicitly credits · reports using a method from · method reported as used by · applies parts of · parts applied by · discusses · reports evaluation of. A missing record does not show that the relation does not exist.
What the document states
A limited selection of what this document states, each with its passage. It describes the text, not whether anyone acted on it.
- StatementRAISE framework of four components across pre-training, post-training and inference-time input/output processing“The RAISE framework comprises four integral components (RAISE-1 to RAISE-4), corresponding to pre-training, post-training, and inference-time input/output processing.”Section on safety (RAISE)Inspect claim & evidence ↗
- StatementRAISE-1: safety classification models filtering pre-training data“At the pre-training phase, we implement a safety model for pretraining data filtration.”RAISE-1: Pre-training SafetyInspect claim & evidence ↗