second-state/jina-embeddings-v2-small-en-GGUF

Same weights, converted vs jinaai/jina-embeddings-v2-small-en. Same weights stored in another dtype (F16 → F16/F32), plus 4 new tensors.

Tensors changed: Embeddings 0/4, Norms 0/16, Attention 0/32, MLP 0/8

On the Hub · Downloads on Model Pulse