| { |
| "architectures": [ |
| "SiglipForImageClassification" |
| ], |
| "id2label": { |
| "0": "Baked Potato", |
| "1": "Crispy Chicken", |
| "2": "Donut", |
| "3": "Fries", |
| "4": "Hot Dog", |
| "5": "Sandwich", |
| "6": "Taco", |
| "7": "Taquito", |
| "8": "Apple Pie", |
| "9": "Burger", |
| "10": "Butter Naan", |
| "11": "Chai", |
| "12": "Chapati", |
| "13": "Cheesecake", |
| "14": "Chicken Curry", |
| "15": "Chole Bhature", |
| "16": "Dal Makhani", |
| "17": "Dhokla", |
| "18": "Fried Rice", |
| "19": "Ice Cream", |
| "20": "Idli", |
| "21": "Jalebi", |
| "22": "Kaathi Rolls", |
| "23": "Kadai Paneer", |
| "24": "Kulfi", |
| "25": "Masala Dosa", |
| "26": "Momos", |
| "27": "Omelette", |
| "28": "Paani Puri", |
| "29": "Pakode", |
| "30": "Pav Bhaji", |
| "31": "Pizza", |
| "32": "Samosa", |
| "33": "Sushi" |
| }, |
| "initializer_factor": 1.0, |
| "label2id": { |
| "Apple Pie": 8, |
| "Baked Potato": 0, |
| "Burger": 9, |
| "Butter Naan": 10, |
| "Chai": 11, |
| "Chapati": 12, |
| "Cheesecake": 13, |
| "Chicken Curry": 14, |
| "Chole Bhature": 15, |
| "Crispy Chicken": 1, |
| "Dal Makhani": 16, |
| "Dhokla": 17, |
| "Donut": 2, |
| "Fried Rice": 18, |
| "Fries": 3, |
| "Hot Dog": 4, |
| "Ice Cream": 19, |
| "Idli": 20, |
| "Jalebi": 21, |
| "Kaathi Rolls": 22, |
| "Kadai Paneer": 23, |
| "Kulfi": 24, |
| "Masala Dosa": 25, |
| "Momos": 26, |
| "Omelette": 27, |
| "Paani Puri": 28, |
| "Pakode": 29, |
| "Pav Bhaji": 30, |
| "Pizza": 31, |
| "Samosa": 32, |
| "Sandwich": 5, |
| "Sushi": 33, |
| "Taco": 6, |
| "Taquito": 7 |
| }, |
| "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": "4.50.0", |
| "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" |
| } |
| } |
|
|
