monatis

↗ HN profile [ 39.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. We published a a distilled version of baai/bge-m3 with 8 layers. It provides 2.4x higher throughput with Pearson Cosine = 0.9691 and Spearman Cosine = 0.965. It quickly became our default embedder model for all our…

  2. Extracting clean text from PDFs is still a mess. Tools like dockling and marker do a decent job—but they’re slow and resource-hungry. pymupdf4llm is fast, but it’s AGPL-licensed, which means you'd need to open-source…