mradermacher/k-12b-GGUF

Quantization (fewer layers) vs ThomasTheMaker/k-12b. mradermacher/k-12b-GGUF matches part of ThomasTheMaker/k-12b (626 of its 1065 tensors; the rest of ThomasTheMaker/k-12b has no counterpart). On the shared part: mradermacher/k-12b-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

On the Hub · Downloads on Model Pulse