added onnx

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
+  "_name_or_path": "/content/distilbert-base-multilingual-cased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 384,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -29,7 +28,6 @@
     "16": "LABEL_16"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1536,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -49,17 +47,17 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "torch_dtype": "float32",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "transformers_version": "4.44.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 250037
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d42a3ba75adf65462c2a5132b58cd0419eba6423439d38ef0895d9ce20b34dd
-size 470664764
+oid sha256:79bd4c961dd02071df3e45692e3b196805c826224f919e2679f0cb9258fcb6bd
+size 541363516

unigram.json → onnx/model.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
-size 14763260
+oid sha256:d1e34b3fe865c0b62e49c163ad10c4ab64b7210e208f1095f968c1b89c91e330
+size 541486659

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70533cd601f21f138c8827307da1e142238ccb5f8b915fb8c61a51b3227caf6c
+size 135753249

quantize_config.json

@@ -0,0 +1,35 @@
+{
+    "per_channel": false,
+    "reduce_range": true,
+    "per_model_config": {
+        "model": {
+            "op_types": [
+                "Gather",
+                "Relu",
+                "Reshape",
+                "Unsqueeze",
+                "ReduceMean",
+                "Pow",
+                "Where",
+                "Equal",
+                "Constant",
+                "Slice",
+                "Erf",
+                "Sub",
+                "MatMul",
+                "Shape",
+                "Sqrt",
+                "Cast",
+                "Gemm",
+                "Expand",
+                "Softmax",
+                "Add",
+                "Concat",
+                "Div",
+                "Mul",
+                "Transpose"
+            ],
+            "weight_type": "QInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -1,48 +1,34 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
+    "content": "[CLS]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
+    "content": "[MASK]",
+    "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "sep_token": {
-    "content": "</s>",
+    "content": "[SEP]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "[UNK]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
-size 17082832
+oid sha256:7d76a4d25ebe8f217654f1039bd991bfc96e7c2cd36e6d28aff941783ed1e9c8
+size 2919460

tokenizer_config.json

@@ -1,64 +1,59 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "do_lower_case": true,
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
-  "max_length": 128,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
-  "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
-  "sep_token": "</s>",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b894dfd5dfa4dd424ce8a12f04180f4166fafa716af6c53cc59dfe08c60790
-size 5176
+oid sha256:7dd08b51ecf04e68f191fc1644771888d7cc109cae699c3ea3fff0c02ead62be
+size 5240