'CLIPVisionConfig' object has no attribute 'vocab_size'

[kwen2501]

CI failure caused by HF changes.

test/hf_test.py:637: 
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
test/hf_test.py:343: in generate_inputs_for_model
    model.config.vocab_size
_ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 

self = CLIPVisionConfig {
  "attention_dropout": 0.0,
  "dropout": 0.0,
  "hidden_act": "quick_gelu",
  "hidden_size": 768,
 ...: 3,
  "num_hidden_layers": 12,
  "patch_size": 32,
  "projection_dim": 512,
  "transformers_version": "4.25.0.dev0"
}

key = 'vocab_size'

    def __getattribute__(self, key):
        if key != "attribute_map" and key in super().__getattribute__("attribute_map"):
            key = super().__getattribute__("attribute_map")[key]
>       return super().__getattribute__(key)
E       AttributeError: 'CLIPVisionConfig' object has no attribute 'vocab_size'