MickyMike/SEALGuard-7B
LoRA-style vs SeaLLMs/SeaLLMs-v3-7B-Chat. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of k_proj, q_proj, v_proj changed, in 28 of 28 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 84/196, lm_head 0/1
1 derivatives checked
- mradermacher/SEALGuard-7B-GGUF: Same weights, converted