File size: 1,519 Bytes
ab8d3d5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
{
"_name_or_path": "LinWeizheDragon/PreFLMR_ViT-L",
"architectures": [
"FLMRModelForRetrieval"
],
"auto_map": {
"AutoConfig": "configuration_flmr.FLMRConfig",
"AutoModel": "modeling_flmr.FLMRModelForRetrieval"
},
"context_concat_output_from_text_encoder": true,
"context_concat_output_from_vision_encoder": false,
"dim": 128,
"initializer_range": 0.02,
"load_cpu_extension": false,
"mapping_network_prefix_length": 32,
"mask_instruction_token": ":",
"mask_punctuation": true,
"model_type": "flmr",
"query_concat_output_from_text_encoder": true,
"query_concat_output_from_vision_encoder": true,
"separate_query_and_context_text_encoder": true,
"separate_query_and_context_vision_encoder": false,
"text_config": {
"architectures": [
"BertForMaskedLM"
],
"gradient_checkpointing": false,
"model_type": "flmr_text_model",
"use_cache": true
},
"torch_dtype": "float32",
"transformer_mapping_config_base": "bert-base-uncased",
"transformer_mapping_cross_attention_length": 32,
"transformer_mapping_num_hidden_layers": 1,
"transformers_version": "4.37.2",
"use_transformer_mapping_network": true,
"use_vision_encoder": true,
"vision_config": {
"dropout": 0.0,
"hidden_size": 1024,
"intermediate_size": 4096,
"model_type": "flmr_vision_model",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"patch_size": 14,
"projection_dim": 768
},
"vision_model_version": "openai/clip-vit-large-patch14"
}
|