Update clip model

Add CLIP base models

Add codegen models

Add gpt2 default and causal-lm models

Add `vit-base-patch16-224-in21k` model file

Add vision transformer models

Add albert models

Update seq2seq and causal-lm models to use decoder_model_merged.onnx

Add tokenizers for whisper models

Add whisper family of models

Add distilbart-cnn-12-6 model

Add `flat-t5` small and base models

Add `t5-v1_1` small and base models

Add more sentence-transformers models

Add roberta-base and distilroberta-base models

Add sentence-transformers all-MiniLM-L6-v2 model

Add t5-base model

Fix folder structure

Remove sequence classification for bert-base-multilingual models

Add distilbert-base-uncased-finetuned-sst-2-english

Add v1 models