{ "architectures": [ "Kosmos2_5ForConditionalGeneration" ], "dtype": "bfloat16", "latent_query_num": 2048, "model_type": "kosmos-2.5", "text_config": { "activation_dropout": 0.0, "activation_function": "gelu", "attention_dropout": 0.0, "attention_heads": 16, "dropout": 0, "dtype": "bfloat16", "embed_dim": 1536, "ffn_dim": 6144, "init_std": 0.02, "layer_norm_eps": 1e-05, "layerdrop": 0.0, "layers": 24, "max_position_embeddings": 4096, "model_type": "kosmos_2_5_text_model", "scale_embedding": true, "use_cache": true, "vocab_size": 108488 }, "transformers_version": "4.57.1", "vision_config": { "attention_dropout": 0.0, "dense_act_fn": "gelu_new", "dropout_rate": 0.0, "dtype": "bfloat16", "head_dim": 64, "hidden_size": 1536, "initializer_factor": 1.0, "initializer_range": 1e-10, "intermediate_size": 3968, "layer_norm_eps": 1e-06, "max_length": 4096, "max_num_patches": 4096, "model_type": "kosmos_2_5_vision_model", "num_attention_heads": 24, "num_hidden_layers": 18, "patch_embed_hidden_size": 768 } }