QuantFactory/internlm2-math-plus-1_8b-GGUF
Quantization vs internlm/internlm2-math-plus-1_8b. QuantFactory/internlm2-math-plus-1_8b-GGUF is a GGUF quantization (Q8_0) of the same weights: 49 tensors match exactly and 98 within quantization error.
Tensors changed: Attention 0/24, Norms 0/49, MLP 0/72, Embeddings 0/1, lm_head 0/1