You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

sl-medlar

CA-Embed stage 1: multilingual-e5-large-instruct fine-tuned for Tajik retrieval. final/ = end of training; wise0.5, wise0.7 = weight-space interpolations with the base; checkpoints 300/400/466. records/ = code, bench, held-out set, results, logs (other sub-runs incl. smokes and the aborted incl-kk run: logs only).

Saidzoda AI Lab. Access is granted on request.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Tohirju/sl-medlar

Base model

intfloat/multilingual-e5-large-instruct

Finetuned

(169)

this model