mradermacher/TemptressTensor-10.7B-v0.1a-GGUF
Quantization vs jsfs11/TemptressTensor-10.7B-v0.1a. mradermacher/TemptressTensor-10.7B-v0.1a-GGUF is a GGUF quantization (Q8_0) of the same weights: 97 tensors match exactly and 338 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/97, MLP 0/144, Attention 0/192