mixedbread-ai/mxbai-rerank-large-v2 config.json
Fields
sources/hf-embed-mxbai-rerank-large-v2Notes
Qwen2 architecture, hidden_size 1536, 28 layers, 12 heads, 2 KV heads, max_position_embeddings 32768, intermediate_size 8960, vocab 151936. Cross-encoder reranker using a causal decoder. Primary source for architecture fields.
W10 LOWCONFIDENCE PROVENANCE AUDIT 2026-10-10: re-classified UNCHECKED after an actual re-fetch. Fetched over HTTPS from this host: HTTP 200, the returned file is live JSON and parses. Every architecture field this note names was then read back out of the live config.json and matches the note's value field-for-field. The 0.5 rating therefore marked a lookup nobody had run, not a property of the source: it is the model publisher's own repository, so it is a primary-shaped source, and the one caveat is that it is a mirror for the license-gated originals (see 'a-hosting-platform-is-not-a-vendor' and the gated-repo records). Raised 0.5 -> 0.88, status draft -> verified.
Cross-references
This record references no other records.