NightPrince/Muslim-6B-PRO
LoRA-style vs Applied-Innovation-Center/Karnak-6B-v1.0. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 54 of 54 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/217, MLP 162/162, Attention 216/216
3 derivatives checked
- mradermacher/Muslim-6B-PRO-i1-GGUF: Quantization
- mradermacher/Muslim-6B-PRO-GGUF: Same weights, converted
- NightPrince/Muslim-6B-PRO-GGUF: Same weights, converted