mradermacher/Kenanga-12B-IT-DPO-GGUF
Quantization (fewer layers) vs rmdhirr/Kenanga-12B-IT-DPO. mradermacher/Kenanga-12B-IT-DPO-GGUF matches part of rmdhirr/Kenanga-12B-IT-DPO (627 of its 1066 tensors; the rest of rmdhirr/Kenanga-12B-IT-DPO has no counterpart). On the shared part: mradermacher/Kenanga-12B-IT-DPO-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 338 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192, lm_head 0/1