Hugging Face's logo

onnx-community
/
Salesforce_blip-image-captioning-base

ONNX
Model card Files
xet
 Community
johnpaultaken commited on
Commit
fabeaa0
·
verified ·
1 Parent(s): 679c75b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -3,4 +3,7 @@ license: bsd-3-clause
3
  ---
4
  Model split into two vision_model and text_decoder.
5
  Run the vision model once and capture the outputs encoder_hidden_states and encoder_attention_mask.
6
- Feed them as inputs to the text decoder and generate the image caption.
 
 
 
 
3
  ---
4
  Model split into two vision_model and text_decoder.
5
  Run the vision model once and capture the outputs encoder_hidden_states and encoder_attention_mask.
6
+ Feed them as inputs to the text decoder and generate the image caption.
7
+
8
+ converted to onnx from source:
9
+ https://huggingface.co/Salesforce/blip-image-captioning-base