GLM-4.7-REAP-25P-W4A16

{
  "_from_model_config": true,
  "do_sample": true,
  "pad_token_id": 151329,
  "eos_token_id": [
    151329,
    151336,
    151338
  ],
  "top_p": 0.95,
  "temperature": 0.8,
  "repetition_penalty": 1.05,
  "top_k": 40,
  "min_p": 0.0,
  "transformers_version": "4.57.3"
}

@article{lasby2025reap,
  title={REAP the Experts: Why Pruning Prevails for One-Shot MoE Compression},
  author={Lasby, Mike and Lazarevich, Ivan and Sinnadurai, Nish and Lie, Sean and Ioannou, Yani and Thangarasa, Vithursan},
  journal={arXiv preprint arXiv:2510.13999},
  year={2025},
  url={https://arxiv.org/abs/2510.13999}
}