mradermacher/MoE-Girl-800MA-3BT-GGUF

Same weights, converted vs allura-org/MoE-Girl-800MA-3BT. Same weights stored in another dtype (BF16 → F16/F32), plus 64 new tensors.

Tensors changed: Embeddings 0/1, other 0/64, Norms 0/65, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse