mradermacher/Barcenas-h-1b-GGUF
Same weights, converted vs Danielbrdz/Barcenas-h-1b. Same weights stored in another dtype (F16 → F16/F32), plus 156 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/81, Attention 0/16
Same weights, converted vs Danielbrdz/Barcenas-h-1b. Same weights stored in another dtype (F16 → F16/F32), plus 156 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/81, Attention 0/16