{ "model_type": "pp_formulanet", "text_config": { "activation_dropout": 0.0, "activation_function": "gelu", "attention_dropout": 0.0, "bos_token_id": 0, "d_model": 512, "decoder_attention_heads": 16, "decoder_ffn_dim": 2048, "decoder_layerdrop": 0.0, "decoder_layers": 8, "dropout": 0.1, "encoder_attention_heads": 16, "encoder_layers": 12, "eos_token_id": 2, "forced_eos_token_id": 2, "init_std": 0.02, "max_position_embeddings": 1024, "num_hidden_layers": 12, "pad_token_id": 1, "scale_embedding": true, "tie_word_embeddings": false, "vocab_size": 50000 }, "vision_config": { "image_size": 768, "output_channels":256, "num_channels":3, "patch_size":16, "hidden_act":"gelu", "layer_norm_eps":1e-6, "attention_dropout":0.0, "qkv_bias":true, "use_abs_pos":true, "use_rel_pos":true, "window_size":14, "hidden_size": 768, "num_hidden_layers": 12, "num_attention_heads": 12, "global_attn_indexes": [2, 5, 8, 11], "mlp_dim": 3072, "post_conv_in_channels": 256, "post_conv_mid_channels": 512, "post_conv_out_channels": 1024, "decoder_hidden_size": 512 } }