mradermacher/Sailor2-14B-SFT-GGUF
Quantization vs sail/Sailor2-14B-SFT. mradermacher/Sailor2-14B-SFT-GGUF is a GGUF quantization (Q6_K) of the same weights: 385 tensors match exactly and 386 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1