mradermacher/daVinci-Dev-72B-MT-GGUF
Quantization vs GAIR/daVinci-Dev-72B-MT. mradermacher/daVinci-Dev-72B-MT-GGUF is a GGUF quantization (Q8_0) of the same weights: 401 tensors match exactly and 562 within quantization error.
Tensors changed: Embeddings 0/1, Attention 0/560, MLP 0/240, lm_head 0/1, Norms 0/161