second-state/jina-embeddings-v2-base-zh-GGUF

Same weights, converted vs jinaai/jina-embeddings-v2-base-zh. Same weights stored in another dtype (F16 → F16/F32), plus 12 new tensors.

Tensors changed: Embeddings 0/4, Norms 0/48, Attention 0/96, MLP 0/24

On the Hub · Downloads on Model Pulse