README.md

metadata

license: mit
language:
  - en
pipeline_tag: summarization
library_name: transformers.js

https://huggingface.co/JustinDu/BARTxiv with ONNX weights to be compatible with Transformers.js.

Steps to get ONNX quantized weights

1. Use optimum-cli to convert the PyTorch weights to ONNX format.

optimum-cli export onnx --model JustinDu/BARTxiv BARTxiv_onnx

2. Use the quantize script in the Transformers.js repo to quantize the ONNX weights.

python -m scripts.quantize --input_folder BARTxiv_onnx --output_folder BARTxiv_onnx/onnx

Move the .onnx files in the BARTxiv_onnx folder to BARTxiv_onnx/onnx (these are the FP32 weights).