Hugging Face's logo

Intel
/
xlm-roberta-base-mrpc-int8-dynamic-inc

Text Classification Transformers ONNX
English xlm-roberta text-classfication int8 Intel® Neural Compressor PostTrainingDynamic Inference Endpoints
Model card Files Community
1pikachu1111 commited on
Commit
f3c23e3
•
1 Parent(s): b7ae378

update int8 onnx model and readme

Browse files

Signed-off-by: dujun <jun.du@intel.com>

Files changed (2) hide show
  1. README.md +3 -3
  2. model.onnx +2 -2
README.md CHANGED
@@ -13,7 +13,7 @@ metrics:
13
  - f1
14
  ---
15
 
16
- # INT8 roberta base finetuned MRPC
17
 
18
  ## Post-training dynamic quantization
19
 
@@ -27,8 +27,8 @@ The original fp32 model comes from the fine-tuned model [Intel/xlm-roberta-base-
27
 
28
  | |INT8|FP32|
29
  |---|:---:|:---:|
30
- | **Accuracy (eval-f1)** |0.8945|0.9010|
31
- | **Model size (MB)** |275|1061|
32
 
33
 
34
  #### Load ONNX model:
13
  - f1
14
  ---
15
 
16
+ # INT8 xlm-roberta base finetuned MRPC
17
 
18
  ## Post-training dynamic quantization
19
 
27
 
28
  | |INT8|FP32|
29
  |---|:---:|:---:|
30
+ | **Accuracy (eval-f1)** |0.8966|0.9010|
31
+ | **Model size (MB)** |354|1061|
32
 
33
 
34
  #### Load ONNX model:
model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6d813dd10c5fe77b93e9f93b50fe31b73f84c18cbb223b3ee126d728dadb4ea
3
- size 287513036
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b64eb841911f82bf28d8f832429f0dad30731cb47eccda96944af48d84f288d9
3
+ size 370569392