| { | |
| "model_type": "tipsv2", | |
| "architectures": [ | |
| "TIPSv2Model" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_tips.TIPSv2Config", | |
| "AutoModel": "modeling_tips.TIPSv2Model" | |
| }, | |
| "patch_size": 14, | |
| "img_size": 448, | |
| "init_values": 1.0, | |
| "num_register_tokens": 1, | |
| "vocab_size": 32000, | |
| "max_len": 64, | |
| "vision_fn": "vit_base", | |
| "embed_dim": 768, | |
| "text_hidden_size": 768, | |
| "text_mlp_dim": 3072, | |
| "text_num_heads": 12, | |
| "text_num_layers": 12, | |
| "ffn_layer": "mlp", | |
| "temperature": 0.005065968260169029 | |
| } |