bartowski/granite-embedding-278m-multilingual-GGUF

Same weights, converted vs ibm-granite/granite-embedding-278m-multilingual. Same weights stored in another dtype (BF16 → F16/F32).

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

On the Hub · Downloads on Model Pulse