legraphista/datagemma-rag-27b-it-IMat-GGUF

Same weights, converted vs google/datagemma-rag-27b-it. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/185, MLP 0/138, Attention 0/184

On the Hub · Downloads on Model Pulse