upload int8 onnx model

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

README.md

@@ -1,3 +1,38 @@
 ---
 license: mit
+tags:
+- text-classfication
+- int8
+- Intel® Neural Compressor
+- neural-compressor
+- PostTrainingStatic
+- onnx
+datasets:
+- glue
+metrics:
+- f1
 ---
+# INT8 camembert-base-mrpc
+
+##  Post-training static 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/deberta-v3-base-mrpc](https://huggingface.co/Intel/deberta-v3-base-mrpc).
+
+#### Test result
+
+|   |INT8|FP32|
+|---|:---:|:---:|
+| **Accuracy (eval-f1)** |0.9185|0.9223|
+| **Model size (MB)**  |361|705|
+
+
+#### Load ONNX model:
+
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+model = ORTModelForSequenceClassification.from_pretrained('Intel/deberta-v3-base-mrpc-int8-static')
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "Intel/deberta-v3-base-mrpc",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "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-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767ec514595d21b8a9f58ed2bf0f2c04c10d2aa4718b1b5c7fcaf1b239c6b7d4
+size 378454189

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}