add model

README.md

@@ -1,3 +1,17 @@
 ---
 license: apache-2.0
+datasets:
+- sst2
+- glue
 ---
+This model is a fork of https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english , quantized using dynamic Post-Training Quantization (PTQ) with ONNX Runtime and 🤗 Optimum library.
+
+It achieves 0.901 on the validation set.
+
+To load this model:
+
+```python
+from optimum.onnxruntime import ORTModelForSequenceClassification
+
+model = ORTModelForSequenceClassification.from_pretrained("fxmarty/distilbert-base-uncased-finetuned-sst-2-english-int8-dynamic")
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,3 @@
+{
+    "accuracy": 0.9013761467889908
+}

model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7ab313ff70257c0099095793bcf0f224b1264047e62a1a2e89e0c1b38a6cc7a
+size 138748915

ort_config.json

@@ -0,0 +1,30 @@
+{
+  "_commit_hash": null,
+  "opset": null,
+  "optimization": {},
+  "optimum_version": "1.4.1.dev0",
+  "quantization": {
+    "activations_dtype": "QUInt8",
+    "activations_symmetric": false,
+    "format": "QOperator",
+    "is_static": false,
+    "mode": "IntegerOps",
+    "nodes_to_exclude": [],
+    "nodes_to_quantize": [],
+    "operators_to_quantize": [
+      "MatMul",
+      "Add"
+    ],
+    "per_channel": false,
+    "qdq_add_pair_to_weight": false,
+    "qdq_dedicated_pair": false,
+    "qdq_op_type_per_channel_support_to_axis": {
+      "MatMul": 1
+    },
+    "reduce_range": false,
+    "weights_dtype": "QInt8",
+    "weights_symmetric": true
+  },
+  "transformers_version": "4.23.0.dev0",
+  "use_external_data_format": false
+}

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512, "do_lower_case": true}