soob3123/amoral-gemma3-27B-v2-qat
LoRA-style vs google/gemma-3-27b-it-qat-q4_0-unquantized. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, o_proj, q_proj, v_proj changed, in 62 of 62 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/484, MLP 0/294, Attention 248/464, other 0/1
2 derivatives checked
- mradermacher/amoral-gemma3-27B-v2-qat-i1-GGUF: Quantization (fewer layers)
- mradermacher/amoral-gemma3-27B-v2-qat-GGUF: Quantization (fewer layers)