mradermacher/Gemma-LN-SFT-GGUF

Quantization (fewer layers) vs Delta-Vector/Pascal-12B. mradermacher/Gemma-LN-SFT-GGUF matches part of Delta-Vector/Pascal-12B (626 of its 1065 tensors; the rest of Delta-Vector/Pascal-12B has no counterpart). On the shared part: mradermacher/Gemma-LN-SFT-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