Madras1/Gemma-4-E4B-Abliterated-Uncensored
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, o_proj changed, in 27 of 42 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 53/606, Norms 0/484, other 0/261, Attention 27/719, Embeddings 0/6
2 derivatives checked
- mradermacher/Gemma-4-E4B-Abliterated-Uncensored-i1-GGUF: Quantization (fewer layers)
- mradermacher/Gemma-4-E4B-Abliterated-Uncensored-GGUF: Same weights, converted (fewer layers)