xCloudinfo/Gemma-4-26B-A4B-TAIDE-zhTW
LoRA-style vs google/gemma-4-26B-A4B-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 30 of 30 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, MLP 0/231, Norms 0/433, other 0/122, Attention 115/223
2 derivatives checked
- xCloudinfo/Gemma-4-26B-A4B-TAIDE-zhTW-GGUF: Quantization
- xCloudinfo/Gemma-4-26B-A4B-TAIDE-zhTW-abliterated-GGUF: Quantization