hooman650

/

bge-m3-onnx-o4

like 4

I have question : in the embeddings, why you are not use

inputs = tokenizer(pairs, padding=True, truncation=True, return_tensors='pt', max_length=512)
sentence_embeddings = model(**inputs)[0][:, 0]

(from https://huggingface.co/hooman650/bge-large-en-v1.5-onnx-o4)

because your example code resulted to another dimension for embedding [17.1024]. But your code in https://huggingface.co/hooman650/bge-large-en-v1.5-onnx-o4 is correct [1024]

Thanks