Upload 8 files

first upload of ONNX converted quantized models

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "ldenoue/distilbert-punctuator",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.25,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "QUESTIONMARK",
+    "1": "EXLAMATIONMARK",
+    "2": "COMMA",
+    "3": "O",
+    "4": "PERIOD"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "COMMA": 2,
+    "EXLAMATIONMARK": 1,
+    "O": 3,
+    "PERIOD": 4,
+    "QUESTIONMARK": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.33.2",
+  "vocab_size": 30522
+}

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39c99d61694332364c710a92988a591502f60d932cf5c28f18b92be0ad1c01ba
+size 66985523

quantize_config.json

@@ -0,0 +1,33 @@
+{
+    "per_channel": true,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "MatMul",
+                "Equal",
+                "Gather",
+                "Mul",
+                "Add",
+                "Transpose",
+                "Shape",
+                "Softmax",
+                "Pow",
+                "ReduceMean",
+                "Slice",
+                "Div",
+                "Sub",
+                "Where",
+                "Sqrt",
+                "Unsqueeze",
+                "Expand",
+                "Erf",
+                "Concat",
+                "Constant",
+                "Cast",
+                "Reshape"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}