| { | |
| "architectures": [ | |
| "MuseGlimmerVisionModel" | |
| ], | |
| "dtype": "float32", | |
| "hidden_act": "gelu", | |
| "hidden_size": 32, | |
| "intermediate_size": 37, | |
| "layer_norm_eps": 1e-05, | |
| "layer_types": [ | |
| "window_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 512, | |
| "merge_size": 1, | |
| "model_type": "muse_glimmer_vision", | |
| "num_attention_heads": 2, | |
| "num_hidden_layers": 2, | |
| "patch_size": 2, | |
| "patch_temporal": 2, | |
| "pos_emb_height": 4, | |
| "pos_emb_width": 4, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| }, | |
| "transformers_version": "5.16.0.dev0" | |
| } | |