Instructions to use treadon/mlx-nucleus-image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use treadon/mlx-nucleus-image with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir mlx-nucleus-image treadon/mlx-nucleus-image
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
File size: 696 Bytes
ca7ff33 | 1 | {"_class_name": "NucleusMoEImageTransformer2DModel", "_diffusers_version": "0.38.0.dev0", "patch_size": 2, "in_channels": 64, "out_channels": 16, "num_layers": 32, "attention_head_dim": 128, "num_attention_heads": 16, "num_key_value_heads": 4, "joint_attention_dim": 4096, "axes_dims_rope": [16, 56, 56], "mlp_ratio": 4.0, "moe_enabled": true, "dense_moe_strategy": "leave_first_three_blocks_dense", "num_experts": 64, "moe_intermediate_dim": 1344, "capacity_factors": [0.0, 0.0, 0.0, 4.0, 4.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0], "use_sigmoid": false, "route_scale": 2.5, "use_grouped_mm": true} |