mradermacher/bge-reranker-v2-gemma-GGUF

Same weights, converted vs BAAI/bge-reranker-v2-gemma. Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/37, MLP 0/54, Attention 0/72

On the Hub · Downloads on Model Pulse