mradermacher/tigerlily-r1-GGUF
Quantization (fewer layers) vs cathuriges/tigerlily-r1. mradermacher/tigerlily-r1-GGUF matches part of cathuriges/tigerlily-r1 (627 of its 1066 tensors; the rest of cathuriges/tigerlily-r1 has no counterpart). On the shared part: mradermacher/tigerlily-r1-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 338 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192