hotchpotch/

vespa-onnx-intfloat-multilingual-e5-large

<component id="me5_large" type="hugging-face-embedder">
    <transformer-model
        url="https://huggingface.co/hotchpotch/vespa-onnx-intfloat-multilingual-e5-large/resolve/main/intfloat-multilingual-e5-large_fp16.onnx" />
    <!-- or int8 quantization model
    <transformer-model
    url="https://huggingface.co/hotchpotch/vespa-onnx-intfloat-multilingual-e5-large/resolve/main/intfloat-multilingual-e5-large_quantized.onnx"
    />
    -->
    <tokenizer-model
        url="https://huggingface.co/hotchpotch/vespa-onnx-intfloat-multilingual-e5-large/resolve/main/tokenizer.json" />
    <normalize>true</normalize>
    <pooling-strategy>mean</pooling-strategy>
</component>

# FP16 model has a larger file size, which can result in longer deployment times.
vespa deploy --wait 1800 .

# https://github.com/vespa-engine/sample-apps/blob/master/simple-semantic-search/export_hf_model_from_hf.py
./export_hf_model_from_hf.py --hf_model intfloat/multilingual-e5-large --output_dir me5-large

# https://github.com/vespa-engine/sample-apps/blob/master/simple-semantic-search/export_hf_model_from_hf.py
./export_hf_model_from_hf.py --hf_model intfloat/multilingual-e5-large --output_dir me5-large

# https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/python/tools/transformers/float16.py

import onnx
from onnxruntime.transformers.float16 import convert_float_to_float16

onnx_model = onnx.load("me5-large/intfloat-multilingual-e5-large.onnx")
model_fp16 = convert_float_to_float16(onnx_model, disable_shape_infer=True)
onnx.save(model_fp16, "me5-large/intfloat-multilingual-e5-large_fp16.onnx")