ThomasTheMaker/k-4b
LoRA-style vs unsloth/gemma-3-4b-it. 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 34 of 34 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/316, MLP 102/210, Attention 136/352, other 0/1
1 derivatives checked
- mradermacher/k-4b-GGUF: LoRA-style (fewer layers)