Iloqt/Barcenas-StyleTune-31B-Fable
Same weights, repacked vs Danielbrdz/Barcenas-31b-Fable. Same weights in different files (re-saved, re-sharded or new metadata), plus 1 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/361, other 0/60, MLP 0/180, Attention 0/230
3 derivatives checked
- mradermacher/Barcenas-StyleTune-31B-Fable-i1-GGUF: Quantization
- mradermacher/Barcenas-StyleTune-31B-Fable-GGUF: Quantization
- Iloqt/Barcenas-StyleTune-31B-Fable-GGUF: Quantization