mradermacher/ReWiz-Llama-3.2-3B-fix-config-GGUF

Same weights, converted vs djuna/ReWiz-Llama-3.2-3B-fix-config. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse