wangzhang/gemma-4-E4B-it-abliterix
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, k_proj, o_proj, q_proj changed, in 38 of 42 layers; norms, biases and embeddings are untouched.
Tensors changed: MLP 24/606, Norms 0/484, other 0/261, Attention 65/719, Embeddings 0/6
4 derivatives checked
- mradermacher/gemma-4-E4B-it-abliterix-i1-GGUF: Quantization (fewer layers)
- mradermacher/gemma-4-E4B-it-abliterix-GGUF: Same weights, converted (fewer layers)
- zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-8bit-int8-affine: Quantization
- zecanard/gemma-4-E4B-it-uncensored-abliterix-MLX-4bit-mixed_4_6: Quantization