ertghiu256/gemma-4-e2b-gemini-opus-reasoning-distill
LoRA-style vs google/gemma-4-E2B-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 35 of 35 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 105/585, Norms 0/453, other 0/240, Attention 140/727, Embeddings 0/6
1 derivatives checked
- kirilldual0987/rumeni-1-nano-GGUF: LoRA-style (fewer layers)