mradermacher/MoE-Girl-1BA-7BT-GGUF

Same weights, converted vs allura-org/MoE-Girl-1BA-7BT. Same weights stored in another dtype (BF16/F32 → F16/F32), plus 48 new tensors.

Tensors changed: MLP 0/16, Embeddings 0/1, Norms 0/65, Attention 0/64, lm_head 0/1

On the Hub · Downloads on Model Pulse