Saidzoda-Tajik-E5-Large: Fine-Tuning a 560M Embedder for Tajik Retrieval

arXiv:2611.00592v1 Announce Type: new Abstract: Finding the passage that answers a question is the first step of most practical systems built on documents, and for Tajik we found no openly described model for it. We present Saidzoda-Tajik-E5-Large, a Tajik text embedder built from multilingual-e5-la

Der Artikeltext wird beim nächsten Sync nachgeladen. Original bei arXiv cs.CL lesen