PrinceRansom7/gemma4-e2b-it-regulatory-obligation-v1
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 k_proj, o_proj, q_proj, v_proj changed, in 35 of 35 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 0/585, Norms 0/453, other 0/240, Attention 140/727, Embeddings 0/6
1 derivatives checked
- mradermacher/gemma4-e2b-it-regulatory-obligation-v1-GGUF: Same weights, converted (fewer layers)