bartowski/PocketDoc_Dans-SakuraKaze-V1.0.0-12b-GGUF

Same weights, converted vs PocketDoc/Dans-SakuraKaze-V1.0.0-12b. Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1

On the Hub · Downloads on Model Pulse