mradermacher/ShantiGPT-GGUF
Quantization vs y4shg/JyotiGPT. mradermacher/ShantiGPT-GGUF is a GGUF quantization (F16) of the same weights: 121 tensors match exactly and 169 within quantization error.
Tensors changed: other 0/1, Attention 0/168, MLP 0/72, Norms 0/49