Apertus: Democratizing Open and Compliant LLMs for Global Language Environments · HackerPapers discussions

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments — mentioned by reconnecting

Mon, 20 Apr 2026 07:11:52 GMT

Tech report: https://arxiv.org/pdf/2509.14233

Paper and discussion history. A mention is not an endorsement.

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments — mentioned by cristoperb

Mon, 20 Apr 2026 04:22:38 GMT

I haven't tried it for anything myself yet. The paper provides several benchmarks. The emphasis during training was on multi-language support (over 1800 languages are represented in its pre-training data, which is 40% non-English) and non-copyrighted training data... and the benchmarks seem to suffer for it. https://arxiv.org/abs/2509.14233

Paper and discussion history. A mention is not an endorsement.

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments — HN submission

Mon, 22 Sep 2025 17:37:00 GMT

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.