tensorblock/sail_Sailor2-1B-GGUF
Quantization vs sail/Sailor2-1B. tensorblock/sail_Sailor2-1B-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 241 tensors match exactly and 338 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/336