jinaai/jina-embeddings-v5-omni-nano-retrieval-GGUF
Same weights, converted (fewer layers) vs jinaai/jina-embeddings-v5-omni-nano-retrieval. jinaai/jina-embeddings-v5-omni-nano-retrieval-GGUF matches part of jinaai/jina-embeddings-v5-omni-nano-retrieval (110 of its 752 tensors; the rest of jinaai/jina-embeddings-v5-omni-nano-retrieval has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/48