LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2509.12539/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTLEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations — mentioned by navarhttps://news.ycombinator.com/item?id=46631788urn:hackerpapers:mention:2509.12539:46631788Thu, 15 Jan 2026 12:59:18 GMT<p>For the retrieval stage, we have developed a highly efficient, CPU-only-friendly text embedding model: https://huggingface.co/MongoDB/mdbr-leaf-ir It ranks #1 on a bunch of leaderboards for models of its size. It can be used interchangeably with the model it has been distilled from (https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v1...). You can see an example comparing semantic (i.e., embeddings-based) search vs bm25 vs hybrid here: http://search-sensei.s3-website-us-east-1.amazonaws.com (warning! It will download ~50MB of data for the model weights and onnx runtime on first load…</p><p><a href="https://hackerpaper.kaipfister.de/p/2509.12539/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.IR