mradermacher/Rae-15B-PT-Ckpts-GGUF
Quantization vs Edens-Gate/Rae-15B-PT-Ckpts. mradermacher/Rae-15B-PT-Ckpts-GGUF is a GGUF quantization (Q8_0) of the same weights: 101 tensors match exactly and 352 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/101, MLP 0/150, Attention 0/200, lm_head 0/1