Deployable Intelligence Models and datasets for "Quantifying deployable intelligence in mixture-of-experts language models". Qwen/Qwen1.5-MoE-A2.7B Text Generation • 14B • Updated Apr 18, 2024 • 485k • 229 deepseek-ai/DeepSeek-V2-Lite Text Generation • 16B • Updated Jun 25, 2024 • 233k • 190 mistralai/Mixtral-8x7B-v0.1 47B • Updated Jul 24, 2025 • 60.3k • 1.83k allenai/c4 Viewer • Updated Jan 9, 2024 • 10.4B • 1.15M • 671
LGViT The checkpoints of LGViT. Paper link: https://arxiv.org/abs/2308.00255 LGViT: Dynamic Early Exiting for Accelerating Vision Transformer Paper • 2308.00255 • Published Aug 1, 2023 FALcon6/LGViT-ViT-Cifar100 Image Classification • Updated Oct 30, 2024 • 10 FALcon6/LGViT-DeiT-Cifar100 Image Classification • Updated Oct 30, 2024 • 8 FALcon6/LGViT-Swin-Cifar100 Image Classification • Updated Oct 30, 2024 • 10
LGViT: Dynamic Early Exiting for Accelerating Vision Transformer Paper • 2308.00255 • Published Aug 1, 2023
DE_models Qwen/Qwen1.5-MoE-A2.7B Text Generation • 14B • Updated Apr 18, 2024 • 485k • 229 deepseek-ai/DeepSeek-V2-Lite Text Generation • 16B • Updated Jun 25, 2024 • 233k • 190 mistralai/Mixtral-8x7B-v0.1 47B • Updated Jul 24, 2025 • 60.3k • 1.83k
MoE Open source MoE IEITYuan/Yuan2-M32-hf Text Generation • Updated May 30, 2024 • 165 • 62 allenai/OLMoE-1B-7B-0924 Text Generation • 7B • Updated Oct 19, 2024 • 111k • 153 microsoft/Phi-3.5-MoE-instruct Text Generation • 42B • Updated Dec 10, 2025 • 136k • 579 Qwen/Qwen1.5-MoE-A2.7B Text Generation • 14B • Updated Apr 18, 2024 • 485k • 229
Deployable Intelligence Models and datasets for "Quantifying deployable intelligence in mixture-of-experts language models". Qwen/Qwen1.5-MoE-A2.7B Text Generation • 14B • Updated Apr 18, 2024 • 485k • 229 deepseek-ai/DeepSeek-V2-Lite Text Generation • 16B • Updated Jun 25, 2024 • 233k • 190 mistralai/Mixtral-8x7B-v0.1 47B • Updated Jul 24, 2025 • 60.3k • 1.83k allenai/c4 Viewer • Updated Jan 9, 2024 • 10.4B • 1.15M • 671
DE_models Qwen/Qwen1.5-MoE-A2.7B Text Generation • 14B • Updated Apr 18, 2024 • 485k • 229 deepseek-ai/DeepSeek-V2-Lite Text Generation • 16B • Updated Jun 25, 2024 • 233k • 190 mistralai/Mixtral-8x7B-v0.1 47B • Updated Jul 24, 2025 • 60.3k • 1.83k
MoE Open source MoE IEITYuan/Yuan2-M32-hf Text Generation • Updated May 30, 2024 • 165 • 62 allenai/OLMoE-1B-7B-0924 Text Generation • 7B • Updated Oct 19, 2024 • 111k • 153 microsoft/Phi-3.5-MoE-instruct Text Generation • 42B • Updated Dec 10, 2025 • 136k • 579 Qwen/Qwen1.5-MoE-A2.7B Text Generation • 14B • Updated Apr 18, 2024 • 485k • 229
LGViT The checkpoints of LGViT. Paper link: https://arxiv.org/abs/2308.00255 LGViT: Dynamic Early Exiting for Accelerating Vision Transformer Paper • 2308.00255 • Published Aug 1, 2023 FALcon6/LGViT-ViT-Cifar100 Image Classification • Updated Oct 30, 2024 • 10 FALcon6/LGViT-DeiT-Cifar100 Image Classification • Updated Oct 30, 2024 • 8 FALcon6/LGViT-Swin-Cifar100 Image Classification • Updated Oct 30, 2024 • 10
LGViT: Dynamic Early Exiting for Accelerating Vision Transformer Paper • 2308.00255 • Published Aug 1, 2023
