second-state/gemma-1.1-7b-it-GGUF

Same weights, converted vs google/gemma-1.1-7b-it. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse