{ "architectures": [ "MiniCPMV" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_minicpm.MiniCPMVConfig", "AutoModel": "modeling_minicpmv.MiniCPMV", "AutoModelForCausalLM": "modeling_minicpmv.MiniCPMV" }, "batch_vision_input": true, "bos_token_id": 151643, "drop_vision_last_layer": false, "dtype": "bfloat16", "eos_token_id": 151645, "gene_config": { "assay": true, "batch_first": true, "cls_classes": 164, "context_length": 1500, "dim_feedforward": 1024, "dim_model": 512, "dropout": 0.0, "learnable_pe": true, "masking_p": 0.15, "modality": true, "model_type": "nicheformer", "n_tokens": 20340, "nheads": 16, "nlayers": 12, "specie": true, "supervised_task": null }, "gene_hidden_size": 512, "gene_max_length": 1500, "gene_vocab_size": 1536, "hidden_act": "silu", "hidden_size": 3584, "image_size": 448, "initializer_range": 0.02, "intermediate_size": 18944, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "minicpmv", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "patch_size": 14, "query_num": 64, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "slice_config": { "max_slice_nums": 9, "model_type": "minicpmv", "patch_size": 14, "scale_resolution": 448 }, "slice_mode": true, "sliding_window": null, "tie_word_embeddings": false, "transformers_version": "4.57.1", "use_cache": true, "use_gene_module": true, "use_image_id": true, "use_sliding_window": false, "version": 2.6, "vision_batch_size": 16, "vision_config": { "attention_dropout": 0.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 1152, "image_size": 980, "intermediate_size": 4304, "layer_norm_eps": 1e-06, "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 27, "patch_size": 14 }, "vocab_size": 151666 }