mradermacher/Luna_12B_V.3-GGUF

Quantization (fewer layers) vs OddTheGreat/Luna_12B_V.3. mradermacher/Luna_12B_V.3-GGUF matches part of OddTheGreat/Luna_12B_V.3 (627 of its 1066 tensors; the rest of OddTheGreat/Luna_12B_V.3 has no counterpart). On the shared part: mradermacher/Luna_12B_V.3-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

On the Hub · Downloads on Model Pulse