AuriAetherwiing/TQ3.5-27B-Musica-v1
LoRA-style vs ArliAI/Qwen3.5-27B-Derestricted. 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, up_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 128/307, Attention 64/560, other 0/1, Norms 0/325
4 derivatives checked
- bartowski/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF: Same weights, converted
- mradermacher/TQ3.5-27B-Musica-v1-i1-GGUF: Quantization
- LyraNovaHeart/AuriAetherwiing_TQ3.5-27B-Musica-v1-GGUF: Same weights, converted
- mradermacher/TQ3.5-27B-Musica-v1-GGUF: Quantization