加载中…
加载中…
onnx/decoder_model_merged.onnx 615 MBonnx/decoder_model.onnx 613 MBonnx/decoder_with_past_model.onnx 613 MBonnx/encoder_model.onnx 343 MBonnx/decoder_model_merged_fp16.onnx 310 MBonnx/encoder_model_fp16.onnx 172 MBonnx/decoder_model_merged_quantized.onnx 159 MBonnx/decoder_model_quantized.onnx 156 MBonnx/decoder_with_past_model_quantized.onnx 156 MBonnx/encoder_model_quantized.onnx 87 MBhttps://huggingface.co/nlpconnect/vit-gpt2-image-captioning with ONNX weights to be compatible with Transformers.js.
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).