mradermacher/solarized-18B-dpo-i1-GGUF
Quantization vs vicgalle/solarized-18B-dpo. mradermacher/solarized-18B-dpo-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 163 tensors match exactly and 569 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/163, MLP 0/243, Attention 0/324, lm_head 0/1