mradermacher/Megatron-Corpus-14B-Exp.v2-GGUF
Quantization vs prithivMLmods/Megatron-Corpus-14B-Exp.v2. mradermacher/Megatron-Corpus-14B-Exp.v2-GGUF is a GGUF quantization (Q8_0) 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