nopp23 commited on
Commit
2e3278a
·
verified ·
1 Parent(s): 6e6698a

Add ONNX exports for in-browser use (Transformers.js): fp32 and per-channel int8

Browse files

Checked on the 763-review held-out split: fp32 identical to PyTorch (F1 0.885); per-channel MatMul int8 F1 0.891 with 1 decision flip.

Files changed (2) hide show
  1. onnx/model.onnx +3 -0
  2. onnx/model_quantized.onnx +3 -0
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7104b48037c74237c10fc0bbb94639bb390bf097128e2a7ba2a838805fe8f1
3
+ size 409344363
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e8c56a42a42c86738429fec8871b539ce983ba39cb2d70aa623515d938bf5a2
3
+ size 153390841