cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-4bit - Каталог нейросетей
Генерация текста

cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-4bit

Добавлено:
cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-4bit

𓌳 REAP𓌳 the Experts: Why Pruning Prevails for One-Shot MoE Compression Introducing GLM-4.7-Flash-REAP-23B-A3B, a memory-efficient compressed variant of GLM-4.7-Flash that maintains near-identical performance while being 25% lighter. This model was created using REAP (Router-weighted Expert Activation Pruning), a novel expert pruning method that selectively removes redundant experts while preserving the router’s independent control over remaining experts. Key features include: — Near-Lossless Performance: Maintains almost identical accuracy on code generation, agentic coding, and function calling tasks compared to the full 355B model — 25% Memory Reduction: Compressed from 355B to 218B parameters, significantly lowering deployment costs and memory requirements — Preserved Capabilities: Retains all core functionalities including code generation, agentic workflows, repository-scale understanding, and function calling — Drop-in C

Модальности:
Генерация текста

Области применения:
Диалог / чат


Задача: Генерация текста
Автор: cyankiwi
Теги: glm4_moe_lite, glm, MOE, pruning, compression, conversational, en, endpoints_compatible
Лайков: 4  |  Загрузок: 780

Открыть на HuggingFace →

Описание основано на материалах HuggingFace. Перевод выполнен автоматически.