Feature Extraction
Transformers
clip
vision
Inference Endpoints
kimihailv commited on
Commit
1ec7966
1 Parent(s): 528b345

Upload 2 files

Browse files
Files changed (2) hide show
  1. config.json +1 -0
  2. weight.pt +3 -0
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"img_encoder": {"backbone": "deit3_base_patch16_224_in21ft1k", "dim": 768, "backbone_type": "vit", "pooling": "cls", "output_dim": 256}, "text_encoder": {"backbone": "google/bert_uncased_L-4_H-768_A-12", "backbone_type": "bert", "unimodal_n_layers": 2, "dim": 768, "pooling": "cls", "context_dim": 768, "output_dim": 256, "head_one_neuron": false}}
weight.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5ea529a78aa90c8c98e616d2ffb40fe68efd97e2189a9132cc84cc6b9632f81
3
+ size 572596251