Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v5-roleplay
LoRA-style vs Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v5-reasoning. 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 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 130/144, Attention 189/336, lm_head 0/1
2 derivatives checked
- mradermacher/NQLSG-Qwen2.5-14B-MegaFusion-v5-roleplay-i1-GGUF: Quantization
- mradermacher/NQLSG-Qwen2.5-14B-MegaFusion-v5-roleplay-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.