ToastyPigeon/Gemma4-E4B-TIES-3mask-r64
LoRA-style vs google/gemma-4-E4B-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 42 of 42 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 121/606, Norms 0/484, other 0/261, Attention 127/719, Embeddings 0/6
2 derivatives checked
- mradermacher/Gemma4-E4B-TIES-3mask-r64-GGUF: Same weights, converted (fewer layers)
- mradermacher/Gemma4-E4B-TIES-3mask-r64-i1-GGUF: Quantization (fewer layers)