| { | |
| "architectures": [ | |
| "Emu3p5VisionVQModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_emu3p5visionvq.Emu3p5VisionVQConfig", | |
| "AutoModel": "modeling_emu3p5visionvq.Emu3p5VisionVQModel" | |
| }, | |
| "attn_resolutions": [ | |
| 16 | |
| ], | |
| "ch": 256, | |
| "ch_mult": [ | |
| 1, | |
| 1, | |
| 2, | |
| 2, | |
| 4 | |
| ], | |
| "codebook_size": 131072, | |
| "double_z": false, | |
| "dropout": 0.0, | |
| "embed_dim": 256, | |
| "in_channels": 3, | |
| "model_type": "Emu3p5VisionVQ", | |
| "num_res_blocks": 4, | |
| "out_ch": 3, | |
| "resolution": 256, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.51.0", | |
| "z_channels": 256 | |
| } | |