unsloth/embeddinggemma-2-GGUF
Same weights, converted vs google/embeddinggemma-2. Same weights stored in another dtype (BF16 → F16/F32), plus 99 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/72, Attention 0/96
Same weights, converted vs google/embeddinggemma-2. Same weights stored in another dtype (BF16 → F16/F32), plus 99 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/72, Attention 0/96