Add INC quantization for VisionEncoderDecoderModel with example (#70)
* Support VisionEncoderDecoderModel and add an example
* rebase branch
* Update for code style
* Update examples/neural_compressor/optical-character-recognition/README.md
Co-authored-by: Ella Charlaix <80481427+echarlaix@users.noreply.github.com>
* Update examples/neural_compressor/optical-character-recognition/README.md
Co-authored-by: Ella Charlaix <80481427+echarlaix@users.noreply.github.com>
* Update examples/neural_compressor/optical-character-recognition/run_trocr.py
Co-authored-by: Ella Charlaix <80481427+echarlaix@users.noreply.github.com>
* Update examples/neural_compressor/optical-character-recognition/run_trocr.py
Co-authored-by: Ella Charlaix <80481427+echarlaix@users.noreply.github.com>
* Update examples/neural_compressor/optical-character-recognition/run_trocr.py
Co-authored-by: Ella Charlaix <80481427+echarlaix@users.noreply.github.com>
* Update example code
* Update README
* limited max eval samples to save tuning time
* Update tuning parameters
* Update for code style
* Remove engine setting
Co-authored-by: Ella Charlaix <80481427+echarlaix@users.noreply.github.com>