mradermacher/dagger-12B_SFT_GRPO-GGUF
Quantization (fewer layers) vs dipta007/dagger-12B_SFT_GRPO. mradermacher/dagger-12B_SFT_GRPO-GGUF matches part of dipta007/dagger-12B_SFT_GRPO (626 of its 1065 tensors; the rest of dipta007/dagger-12B_SFT_GRPO has no counterpart). On the shared part: mradermacher/dagger-12B_SFT_GRPO-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192