Colby/Apertus-8B-openhermes-gguf
LoRA-style vs swiss-ai/Apertus-8B-2509. Colby/Apertus-8B-openhermes-gguf is a GGUF (F16) of different weights. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 64/64, Attention 128/128, lm_head 0/1