vicgalle/franken-SOLAR-18B-v1.0-GGUF
Full fine-tune (fewer layers) vs NousResearch/Nous-Hermes-2-SOLAR-10.7B. NousResearch/Nous-Hermes-2-SOLAR-10.7B matches part of vicgalle/franken-SOLAR-18B-v1.0-GGUF (435 of its 732 tensors; the rest of vicgalle/franken-SOLAR-18B-v1.0-GGUF has no counterpart). On the shared part: vicgalle/franken-SOLAR-18B-v1.0-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 72/97, MLP 144/144, Attention 192/192, lm_head 1/1