{ "_name_or_path": "", "architectures": [ "BiomedCLIPModel" ], "auto_map": { "AutoConfig": "configuration_biomed_clip.BiomedCLIPConfig", "AutoProcessor": "processing_biomed_clip.BiomedCLIPProcessor", "AutoModel": "modeling_biomed_clip.BiomedCLIPModel", "AutoModelForImageClassification": "modeling_biomed_clip.BiomedCLIPForImageClassification" }, "initializer_factor": 1.0, "logit_scale_init_value": 4.4454, "model_type": "clip", "projection_dim": 512, "text_config": { "attention_probs_dropout_prob": 0.1, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "transformers_version": "4.6.0.dev0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522 }, "text_config_dict": { "attention_probs_dropout_prob": 0.1, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "transformers_version": "4.6.0.dev0", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522 }, "text_projection_config": { "hidden_size": 768, "intermediate_size": 640, "projection_dim": 512, "hidden_act": "gelu" }, "text_projection_config_dict": { "hidden_size": 768, "intermediate_size": 640, "projection_dim": 512, "hidden_act": "gelu", "num_hidden_layers": 2 }, "torch_dtype": "float32", "transformers_version": null, "vision_config": { "attention_probs_dropout_prob": 0.0, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 768, "image_size": 224, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "model_type": "vit", "num_attention_heads": 12, "num_channels": 3, "num_hidden_layers": 12, "patch_size": 16, "qkv_bias": true }, "vision_config_dict": { "attention_probs_dropout_prob": 0.0, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 768, "image_size": 224, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "model_type": "vit", "num_attention_heads": 12, "num_channels": 3, "num_hidden_layers": 12, "patch_size": 16, "qkv_bias": true } }