{ "architectures": [ "SiglipForImageClassification" ], "id2label": { "0": "aluminium", "1": "batteries", "2": "cardboard", "3": "disposable plates", "4": "glass", "5": "hard plastic", "6": "paper", "7": "paper towel", "8": "polystyrene", "9": "soft plastics", "10": "takeaway cups" }, "initializer_factor": 1.0, "label2id": { "aluminium": 0, "batteries": 1, "cardboard": 2, "disposable plates": 3, "glass": 4, "hard plastic": 5, "paper": 6, "paper towel": 7, "polystyrene": 8, "soft plastics": 9, "takeaway cups": 10 }, "model_type": "siglip", "problem_type": "single_label_classification", "text_config": { "attention_dropout": 0.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 768, "intermediate_size": 3072, "layer_norm_eps": 1e-06, "max_position_embeddings": 64, "model_type": "siglip_text_model", "num_attention_heads": 12, "num_hidden_layers": 12, "projection_size": 768, "torch_dtype": "float32", "vocab_size": 256000 }, "torch_dtype": "float32", "transformers_version": "4.50.3", "vision_config": { "attention_dropout": 0.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 768, "image_size": 224, "intermediate_size": 3072, "layer_norm_eps": 1e-06, "model_type": "siglip_vision_model", "num_attention_heads": 12, "num_channels": 3, "num_hidden_layers": 12, "patch_size": 16, "torch_dtype": "float32" } }