mradermacher/Matrix-Mini-GGUF

Same weights, converted (fewer layers) vs GenueAI/Matrix-Mini. mradermacher/Matrix-Mini-GGUF matches part of GenueAI/Matrix-Mini (677 of its 2130 tensors; the rest of GenueAI/Matrix-Mini has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/BF16), plus 43 new tensors.

Tensors changed: Embeddings 0/2, Norms 0/296, MLP 0/126, other 0/85, Attention 0/168

On the Hub · Downloads on Model Pulse