{ "_name_or_path": "google/pix2struct-textcaps-base", "architectures": [ "Pix2StructForConditionalGeneration" ], "decoder_start_token_id": 0, "eos_token_id": 1, "initializer_factor": 1.0, "initializer_range": 0.02, "is_encoder_decoder": true, "is_vqa": false, "model_type": "pix2struct", "pad_token_id": 0, "text_config": { "dropout_rate": 0.05, "encoder_hidden_size": 768, "feed_forward_proj": "gated-gelu", "initializer_range": 0.02, "is_gated_act": true, "model_type": "pix2struct_text_model" }, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.39.1", "vision_config": { "attention_dropout": 0.05, "dropout_rate": 0.06, "hidden_dropout_prob": 0.05, "image_size": 384, "initializer_range": 0.02, "layer_norm_bias": false, "mlp_bias": false, "model_type": "pix2struct_vision_model", "num_channels": 3, "patch_size": 16, "projection_dim": 768, "qkv_bias": false } }