| { |
| "architectures": [ |
| "VisionEncoderDecoderModel" |
| ], |
| "decoder": { |
| "activation_dropout": 0.0, |
| "activation_function": "relu", |
| "add_cross_attention": true, |
| "attention_dropout": 0.0, |
| "classifier_dropout": 0.0, |
| "cross_attention_hidden_size": 384, |
| "d_model": 256, |
| "decoder_attention_heads": 8, |
| "decoder_ffn_dim": 1024, |
| "decoder_layerdrop": 0.0, |
| "decoder_layers": 6, |
| "dropout": 0.1, |
| "init_std": 0.02, |
| "is_decoder": true, |
| "layernorm_embedding": true, |
| "max_position_embeddings": 512, |
| "model_type": "trocr", |
| "scale_embedding": true, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "use_cache": false, |
| "use_learned_position_embeddings": true, |
| "vocab_size": 64000 |
| }, |
| "decoder_start_token_id": 33, |
| "encoder": { |
| "attention_probs_dropout_prob": 0.0, |
| "encoder_stride": 16, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 384, |
| "image_size": 384, |
| "initializer_range": 0.02, |
| "intermediate_size": 1536, |
| "layer_norm_eps": 1e-12, |
| "model_type": "deit", |
| "num_attention_heads": 6, |
| "num_channels": 3, |
| "num_hidden_layers": 12, |
| "patch_size": 16, |
| "pooler_act": "tanh", |
| "pooler_output_size": 384, |
| "qkv_bias": true, |
| "torch_dtype": "float32" |
| }, |
| "eos_token_id": 34, |
| "is_encoder_decoder": true, |
| "max_length": null, |
| "model_type": "vision-encoder-decoder", |
| "num_beams": null, |
| "pad_token_id": 31, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.3", |
| "vocab_size": 64000 |
| } |
|
|
