Upload tokenizer

README.md

@@ -1,66 +1,66 @@
 ---
+base_model:
+- dbmdz/bert-base-italian-xxl-uncased
+datasets:
+- sapienzanlp/ami
+language:
+- it
+library_name: transformers
+license: cc-by-nc-sa-4.0
+metrics:
+- accuracy
+- f1
+- recall
+- precision
+pipeline_tag: text-classification
+tags:
+- misogyny
+- italian
 model-index:
 - name: misogyny-detection-it
   results:
   - task:
       type: classification
     dataset:
-      type: text-classification
       name: sapienzanlp/ami
+      type: text-classification
     metrics:
-    - name: test_loss
-      type: loss
+    - type: loss
       value: 0.2205
+      name: test_loss
       verified: false
-    - name: test_accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.9412
+      name: test_accuracy
       verified: false
-    - name: test_f1
-      type: f1
+    - type: f1
       value: 0.942
+      name: test_f1
       verified: false
-    - name: test_precision
-      type: precision
+    - type: precision
       value: 0.9291
+      name: test_precision
       verified: false
-    - name: test_recall
-      type: recall
+    - type: recall
       value: 0.9553
+      name: test_recall
       verified: false
-    - name: test_runtime
-      type: runtime
+    - type: runtime
       value: 13.0069
+      name: test_runtime
       verified: false
-    - name: test_samples_per_second
-      type: samples_per_second
+    - type: samples_per_second
       value: 223.573
+      name: test_samples_per_second
       verified: false
-    - name: test_steps_per_second
-      type: steps_per_second
+    - type: steps_per_second
       value: 6.996
+      name: test_steps_per_second
       verified: false
-    - name: epoch
-      type: epoch
+    - type: epoch
       value: 5
+      name: epoch
       verified: false
-license: cc-by-nc-sa-4.0
-library_name: transformers
-datasets:
-- sapienzanlp/ami
-language:
-- it
-base_model:
-- dbmdz/bert-base-italian-xxl-uncased
-pipeline_tag: text-classification
-tags:
-- misogyny
-- italian
-metrics:
-- accuracy
-- f1
-- recall
-- precision
 ---
 
 # Model Card for Misogyny Detection in Italian

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 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}