{ "model_type": "minimax_h3", "partition": "ref2va", "tasks": [ "ref2va" ], "sigma_shift_scales": { "video": 12.0, "audio": 3.0 }, "fps": 24, "quantization": { "group_size": 64, "bits": 8, "mode": "affine" }, "transformer": { "hidden_size": 5376, "num_layers": 50, "num_attention_heads": 56, "attention_head_dim": 128, "ffn_hidden_size": 14336, "latents_dim": 24, "audio_latents_dim": 32, "text_dim": 5120, "time_embed_dim": 2688, "rope_inv_freq_len": 16 }, "text_encoder": { "hidden": 5120, "layers": 50, "heads": 64, "kv_heads": 8, "head_dim": 128, "intermediate": 25600, "theta": 5000000.0 } }