"""KeyLM model configuration. KeyLM-75M is a from-scratch small language model. Its decoder block is a Qwen3-style layout (grouped-query attention, RoPE, SwiGLU, and per-head QK-RMSNorm), so the configuration inherits Qwen3Config and only overrides the ``model_type`` so the model carries its own identity on the Hub. """ from transformers.models.qwen3.configuration_qwen3 import Qwen3Config class KeyLM75MConfig(Qwen3Config): model_type = "keylm75m"