QK-Normalization Support

[JakobStadlhuber]

The Qwen3 architecture, which introduced new layers (k_norm and q_norm) which is not supported in LM Studio

see here: https://huggingface.co/mlx-community/LightOnOCR-2-1B-8bit/discussions/1

Could this be added?

[JakobStadlhuber]

🥲 Failed to load the model

Failed to load model

Error when loading model: ValueError: Received 56 parameters not in model: 
language_model.model.layers.0.self_attn.k_norm.weight,
language_model.model.layers.0.self_attn.q_norm.weight,
language_model.model.layers.1.self_attn.k_norm.weight,
language_model.model.layers.1.self_attn.q_norm.weight,
language_model.model.layers.10.self_attn.k_norm.weight,
language_model.model.layers.10.self_attn.q_norm.weight,
language_model.model.layers.11.self_attn.k_norm.weight,
language_model.model.layers.11.self_attn.q_norm.weight,
language_model.model.layers.12.self_attn.k_norm.weight,
language_model.model.layers.12.self_attn.q_norm.weight,
language_model.model.layers.13.self_attn.k_norm.weight,
language_model.model.layers.13.self_attn.q_norm.weight,
language_model.model.layers.14.self_attn.k_norm.weight,
language_model.model.layers.14.self_attn.q_norm.weight,
language_model.model.layers.15.self_attn.k_norm.weight,
language_model.model.layers.15.self_attn.q_norm.weight,
language_model.model.layers.16.self_attn.k_norm.weight,
language_model.model.layers.16.self_attn.q_norm.weight,
language_model.model.layers.17.self_attn.k_norm.weight,
language_model.model.layers.17.self_attn.q_norm.weight,
language_model.model.layers.18.self_attn.k_norm.weight,
language_model.model.layers.18.self_attn.q_norm.weight,
language_model.model.layers.19.self_attn.k_norm.weight,
language_model.model.layers.19.self_attn.q_norm.weight,
language_model.model.layers.2.self_attn.k_norm.weight,
language_model.model.layers.2.self_attn.q_norm.weight,
language_model.model.layers.20.self_attn.k_norm.weight,
language_model.model.layers.20.self_attn.q_norm.weight,
language_model.model.layers.21.self_attn.k_norm.weight,
language_model.model.layers.21.self_attn.q_norm.weight,
language_model.model.layers.22.self_attn.k_norm.weight,
language_model.model.layers.22.self_attn.q_norm.weight,
language_model.model.layers.23.self_attn.k_norm.weight,
language_model.model.layers.23.self_attn.q_norm.weight,
language_model.model.layers.24.self_attn.k_norm.weight,
language_model.model.layers.24.self_attn.q_norm.weight,
language_model.model.layers.25.self_attn.k_norm.weight,
language_model.model.layers.25.self_attn.q_norm.weight,
language_model.model.layers.26.self_attn.k_norm.weight,
language_model.model.layers.26.self_attn.q_norm.weight,
language_model.model.layers.27.self_attn.k_norm.weight,
language_model.model.layers.27.self_attn.q_norm.weight,
language_model.model.layers.3.self_attn.k_norm.weight,
language_model.model.layers.3.self_attn.q_norm.weight,
language_model.model.layers.4.self_attn.k_norm.weight,
language_model.model.layers.4.self_attn.q_norm.weight,
language_model.model.layers.5.self_attn.k_norm.weight,
language_model.model.layers.5.self_attn.q_norm.weight,
language_model.model.layers.6.self_attn.k_norm.weight,
language_model.model.layers.6.self_attn.q_norm.weight,
language_model.model.layers.7.self_attn.k_norm.weight,
language_model.model.layers.7.self_attn.q_norm.weight,
language_model.model.layers.8.self_attn.k_norm.weight,
language_model.model.layers.8.self_attn.q_norm.weight,
language_model.model.layers.9.self_attn.k_norm.weight,
language_model.model.layers.9.self_attn.q_norm.weight.