mradermacher/Vigyan-1.5B-4x-MoE-GGUF

Same weights, converted vs shreyansh12183/Vigyan-1.5B-4x-MoE. Same weights stored in another dtype (BF16 → F16/F32), plus 84 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/112, Attention 0/196, lm_head 0/1

On the Hub · Downloads on Model Pulse