q8 embedding layer

#1
by Xenova HF staff - opened
.gitattributes CHANGED
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
37
  onnx/model_q4f16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
38
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
36
  onnx/model_q4f16.onnx_data filter=lfs diff=lfs merge=lfs -text
37
  onnx/model_q4f16.onnx_data_1 filter=lfs diff=lfs merge=lfs -text
38
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ onnx/model_q4f16.onnx_data_2 filter=lfs diff=lfs merge=lfs -text
onnx/model_q4f16.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c33161f7ec7d7e8921b77823185ec9c43ab63a105d63375673f1f579284572c6
3
- size 291159
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22590a08607394348a4b3e08e4e754e3cb69cc41d57c0f0da3259d12479ab6f9
3
+ size 286180
onnx/model_q4f16.onnx_data CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b383cab285b493c5e4e5eb27b343944873becdc6fe53a4a892fbc84617a024b
3
- size 1993777152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ece4ec9512148abd6c4a633447d053b1b8580209d8fbba2d3cb5c2c2c1d3ea
3
+ size 1198196736
onnx/model_q4f16.onnx_data_1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d087f38ea375599203a493fba54083c986eae10e8a66c694c6347b7969775aab
3
- size 1419417600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425d30eab36b5f2e7b40656aaf291888b00a215bc9065bf57f3f5cd3c1b89421
3
+ size 614141952
onnx/model_q4f16.onnx_data_2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1009c9a63b3a8e1aa306058a41de7332513d929cb07ab2fd73db28bffa66c7a2
3
+ size 640548864