| { | |
| "_name_or_path": "roberta-base", | |
| "architectures": [ | |
| "LayoutLMv3ForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "coordinate_size": 128, | |
| "device": "cuda", | |
| "discrete_vae_type": "dvaeforbeit", | |
| "discrete_vae_weight_path": "/mnt/models/models/tokenizer/dvae", | |
| "eos_token_id": 2, | |
| "has_relative_attention_bias": true, | |
| "has_spatial_attention_bias": true, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "input_size": 224, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-05, | |
| "max_2d_position_embeddings": 1024, | |
| "max_position_embeddings": 514, | |
| "max_rel_2d_pos": 256, | |
| "max_rel_pos": 128, | |
| "mim": true, | |
| "model_type": "layoutlmv3", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 1, | |
| "wpa_task": true, | |
| "rel_2d_pos_bins": 64, | |
| "rel_pos_bins": 32, | |
| "second_input_size": 112, | |
| "shape_size": 128, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.12.5", | |
| "type_vocab_size": 1, | |
| "visual_embed": true, | |
| "vocab_size": 50265 | |
| } | |