Scicom-intl/Qwen3-235B-A22B-Instruct-2507-Malaysian
LoRA-style vs Qwen/Qwen3-235B-A22B-Instruct-2507. 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 94 of 94 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, MLP 2149/2245, Norms 0/377, Attention 376/376, lm_head 0/1