Sakalti/Saba2-1.7B

Same weights, converted vs Sakalti/Saba1.5-1.7B. Same weights stored in another dtype (BF16 → F16).

Tensors changed: Embeddings 0/1, Norms 0/55, MLP 0/81, Attention 0/189

1 derivatives checked

• mradermacher/Saba2-1.7B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse