upload int8 onnx model

Signed-off-by: yuwenzho <yuwen.zhou@intel.com>

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,40 @@
 ---
+language: en
 license: mit
+tags:
+- text-classfication
+- int8
+- Intel® Neural Compressor
+- PostTrainingDynamic
+- onnx
+datasets: 
+- mrpc
+metrics:
+- f1
 ---
+
+# INT8 roberta base finetuned MRPC
+
+## Post-training dynamic quantization
+
+### ONNX
+
+This is an INT8 ONNX model quantized with [Intel® Neural Compressor](https://github.com/intel/neural-compressor).
+
+The original fp32 model comes from the fine-tuned model [Intel/xlm-roberta-base-mrpc](https://huggingface.co/Intel/xlm-roberta-base-mrpc).
+
+#### Test result
+
+|   |INT8|FP32|
+|---|:---:|:---:|
+| **Accuracy (eval-f1)** |0.8945|0.9010|
+| **Model size (MB)**  |275|1061|
+
+
+#### Load ONNX model:
+
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+model = ORTModelForSequenceClassification.from_pretrained('Intel/xlm-roberta-base-mrpc-int8-dynamic')
+```
+

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "mrpc",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6d813dd10c5fe77b93e9f93b50fe31b73f84c18cbb223b3ee126d728dadb4ea
+size 287513036

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660