Hugging Face's logo

Bingsu
/
vitB32_bert_ko_small_clip

Feature Extraction Transformers PyTorch Safetensors Korean vision-text-dual-encoder clip Inference Endpoints
Model card Files Community
1
Bingsu commited on
Commit
405853c
•
1 Parent(s): 2913c2d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -50,6 +50,10 @@ tensor([[0.9756, 0.0244]], grad_fn=<SoftmaxBackward0>)
50
  ```python
51
  from transformers import AutoModel, AutoProcessor, pipeline
52
 
 
 
 
 
53
  model = AutoModel.from_pretrained("Bingsu/vitB32_bert_ko_small_clip")
54
  processor = AutoProcessor.from_pretrained("Bingsu/vitB32_bert_ko_small_clip")
55
  pipe = pipeline("zero-shot-image-classification", model=model, feature_extractor=processor.feature_extractor, tokenizer=processor.tokenizer)
50
  ```python
51
  from transformers import AutoModel, AutoProcessor, pipeline
52
 
53
+ pipe = pipeline("zero-shot-image-classification", model="Bingsu/vitB32_bert_ko_small_clip")
54
+
55
+ # or
56
+
57
  model = AutoModel.from_pretrained("Bingsu/vitB32_bert_ko_small_clip")
58
  processor = AutoProcessor.from_pretrained("Bingsu/vitB32_bert_ko_small_clip")
59
  pipe = pipeline("zero-shot-image-classification", model=model, feature_extractor=processor.feature_extractor, tokenizer=processor.tokenizer)