| { | |
| "architectures": [ | |
| "ViltForImageAndTextRetrieval" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "image_size": 384, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_image_length": -1, | |
| "max_position_embeddings": 40, | |
| "modality_type_vocab_size": 2, | |
| "model_type": "vilt", | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 32, | |
| "qkv_bias": true, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.15.0.dev0", | |
| "type_vocab_size": 2, | |
| "vocab_size": 30522 | |
| } | |