𓌳 REAP𓌳 the Experts: Why Pruning Prevails for One-Shot MoE Compression 📄 Paper • 💻 Code • 📝 Blog Important Update regarding GGUF support: A critical bug was recently identified in llama.cpp regarding the scoringfunc` for GLM models (which caused looping and poor output quality). While the base weights are functional, the GGUF files for this model are currently being re-generated to ensure full compatibility with the latest fixes. Status: GGUF files are scheduled for re-upload by January 24, 2026. Recommendation: If you are using local inference via llama.cpp or Unsloth, please refer to the official Unsloth GLM-4.7-Flash documentation for the most stable configuration parameters. Native Support: The BF16/FP16 weights remain compatible with transformers and vLLM` for immediate use. 50% Expert-Pruned GLM-4.7 Flash optimized for code generation, function calling, and agentic workflows. Created using REAP (Router-weighted Expert Activation Pruning) by Cerebras: — Calibrated for Code & Tools: Preserves coding and function-calling capabilities — One-Shot Compression: No fine-tuning required — Drop-in Compatible: Works with vLLM, Transformers, SGLang Cerebras used the same 3 datasets…
Модальности:
Генерация текста
Области применения:
Генерация кода Диалог / чат Вызов функций (Tool use)
Задача: Генерация текста
Автор: Akicou
Теги: glm4_moe_lite, glm, glm4.7, MOE, pruning, compression, reap, cerebras
Лайков: 3 | Загрузок: 69
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
