Luminous-Designs/Qwen3.5-9B-Schwartz-TIES
LoRA-style vs Lambent/Qwen3.5-9B-Base-Thoughtful-Interiority. 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 31 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, Norms 0/221, Attention 32/336, MLP 96/211, other 0/1
1 derivatives checked
- mradermacher/Qwen3.5-9B-Schwartz-TIES-GGUF: Same weights, converted
1 other repos hold byte-for-byte identical weight files.