| { | |
| "_class_name": "MiniMaxH3Transformer3DModel", | |
| "_diffusers_version": "0.41.0.dev0", | |
| "_name_or_path": "/root/.cache/huggingface/hub/models--MiniMaxAI--MiniMax-H3/snapshots/42ed227ee7df40d41602854ae760620d6eb651fe", | |
| "attention_head_dim": 128, | |
| "audio_in_channels": 32, | |
| "ffn_dim": 14336, | |
| "final_norm_eps": 1e-05, | |
| "freq_dim": 256, | |
| "hidden_size": 5376, | |
| "in_channels": 24, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 56, | |
| "num_layers": 50, | |
| "num_refiner_layers": 2, | |
| "patch_size": [ | |
| 1, | |
| 2, | |
| 2 | |
| ], | |
| "qk_norm_eps": 1e-05, | |
| "quantization_config": { | |
| "modules_to_not_convert": [ | |
| "proj_in", | |
| "audio_proj_in", | |
| "context_embedder", | |
| "time_embedder", | |
| "time_proj", | |
| "token_refiner", | |
| "norm_out", | |
| "proj_out", | |
| "audio_proj_out", | |
| "proj_in", | |
| "audio_proj_in", | |
| "time_embedder", | |
| "proj_out", | |
| "audio_proj_out", | |
| "rope", | |
| "proj_in", | |
| "audio_proj_in", | |
| "time_embedder", | |
| "proj_out", | |
| "audio_proj_out", | |
| "rope" | |
| ], | |
| "quant_method": "torchao", | |
| "quant_type": { | |
| "default": { | |
| "_data": { | |
| "use_dynamic_per_tensor_scale": true, | |
| "use_triton_kernel": true | |
| }, | |
| "_type": "NVFP4DynamicActivationNVFP4WeightConfig", | |
| "_version": 1 | |
| } | |
| } | |
| }, | |
| "rope_freq_dim": 16, | |
| "rope_theta": 10000.0, | |
| "text_dim": 5120, | |
| "time_embed_dim": 2688, | |
| "time_embed_hidden_dim": 5376 | |
| } | |