kurugai/Kurugai-EEVE-v1.0
LoRA-style vs yanolja/YanoljaNEXT-EEVE-10.8B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 144/144, Attention 192/192, lm_head 0/1
2 derivatives checked
- mradermacher/Kurugai-EEVE-v1.0-GGUF: Same weights, converted
- kurugai/Kurugai-EEVE-v1.1: Identical copy
1 other repos hold byte-for-byte identical weight files.