Suggestion: Sentence Transformer based on Apertus-8B-Instruct for Swiss GLAM, Memobase & Research
Dear swiss-ai team,
Thank you very much for your impressive work and for making Apertus-8B-Instruct available to the community. This model is a valuable contribution to the Swiss AI ecosystem.
For many use cases in the swiss GLAM sector, in research, and specifically for Memobase, a dedicated Sentence Transformer based on your LLM would be extremely beneficial. Our goal is to enable robust semantic search in multilingual cultural heritage databases, which would directly support institutions like Memobase and similar projects.
Memobase is the Swiss aggregation platform for searching and accessing digitized cultural AV heritage operated by Memoriav, the association for the preservation of AV heritage in Switzerland.
Would you consider training and releasing a (compact) Sentence Transformer derived from Apertus-8B-Instruct as a community resource? This would greatly support Swiss GLAM organizations, Memobase, and the research community.
Thank you for your consideration and for your outstanding work!
Best regards,
Daniel
yes it would be great if the community would help creating embedding models from apertus. this can be done for example by distillation and finetuning on an adjusted embedding objective.
here is some example by another contributor: https://huggingface.co/speakdatawith/Apertus-8B-2509-Encoder