clip-vit-L14-coco / config.json
tomaarsen's picture
tomaarsen HF Staff
Add new SentenceTransformer model
0cb6d4b verified
{
"architectures": [
"CLIPModel"
],
"dtype": "float32",
"initializer_factor": 1.0,
"logit_scale_init_value": 2.6592,
"model_type": "clip",
"projection_dim": 768,
"text_config": {
"attention_dropout": 0.0,
"dropout": 0.0,
"dtype": "float32",
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 77,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"projection_dim": 768,
"use_bfloat16": false,
"vocab_size": 49408
},
"transformers_version": "4.57.0.dev0",
"vision_config": {
"attention_dropout": 0.0,
"dropout": 0.0,
"dtype": "float32",
"hidden_act": "quick_gelu",
"hidden_size": 1024,
"image_size": 224,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-05,
"model_type": "clip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 24,
"patch_size": 14,
"projection_dim": 768,
"use_bfloat16": false
}
}