Add ONNX support for Longformer (#17176)

* Implement ONNX support for Longformer

Fix repo consistency check complaints

Fix value mismatches

Add pooler output for default model

Increase validation atol to accommodate multiple-choice error

Fix copies

Fix chunking for longer sequence lengths

Add future comment

* Fix issue in mask_invalid_locations

* Remove torch imports in configuration_longformer

* Change config access to fix LED

* Push opset version to support tril

* Work in review comments (mostly style)

* Add Longformer to ONNX tests

tests/onnx/test_onnx_v2.py

@@ -212,6 +212,7 @@ PYTORCH_EXPORT_MODELS = {
     ("data2vec-vision", "facebook/data2vec-vision-base"),
     ("perceiver", "deepmind/language-perceiver", ("masked-lm", "sequence-classification")),
     ("perceiver", "deepmind/vision-perceiver-conv", ("image-classification",)),
+    ("longformer", "allenai/longformer-base-4096"),
     ("yolos", "hustvl/yolos-tiny"),
 }