GLM-4.7-Flash-RAZOR-17B-A3B-E32of64
GLM-4.7-Flash with half of its routed experts removed by RAZOR, a training-free expert pruning method. Every MoE layer...
GLM-4.7-Flash with half of its routed experts removed by RAZOR, a training-free expert pruning method. Every MoE layer...
INVALID LANGUAGE PAIR SPECIFIED. EXAMPLE: LANGPAIR=EN|IT USING 2 LETTER ISO OR RFC3066 LIKE ZH-CN. ALMOST ALL LANGUAGES SUPPORTED...
GLM-4.7-Flash-Abliteratex is a rebuilt successor to wangzhang/GLM-4.7-Flash-abliterated. The release focuses on preserving the official checkpoint structure, reducing collateral...
💬 Community: Join the Abliterlitics Discord for discussion, model releases and support. > Forensic analysis by Abliterlitics —...
Эту модель квантовали с использованием квантования смешанной точности oQ. — Тип модели: glm4moelite — Биты: 4 — Размер...
NVFP4 post-training quantization of Olafangensan/GLM-4.7-Flash-heretic for long-context multi-GPU inference with vLLM. > [!IMPORTANT] > The Hugging Face UI...
Эта модель была преобразована в формат MLX из cerebras/GLM-4.7-Flash-REAP-23B-A3B с использованием mlx-lm версии 0.30.5. $ uv run mlxlm.convert...
This is a GLM-4.7-Flash fine-tune, produced at the request of McG-221 through P-E-W’s Heretic (v1.1.0) abliteration engine merged...
𓌳 REAP𓌳 the Experts: Why Pruning Prevails for One-Shot MoE Compression 📄 Paper • 💻 Code • 📝...
Эта модель mlx-community/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill-4bit была преобразована в формат MLX из TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill с использованием mlx-lm версии 0.30.6. Модальности:Генерация текста Области...