Upload tokenizer

README.md

@@ -15,8 +15,8 @@ model-index:
 - name: roberta-base-sentiment140
   results:
   - task:
-      name: Text Classification
       type: text-classification
+      name: Text Classification
     dataset:
       name: sentiment140
       type: sentiment140
@@ -24,18 +24,18 @@ model-index:
       split: train
       args: sentiment140
     metrics:
-    - name: Accuracy
-      type: accuracy
+    - type: accuracy
       value: 0.883
-    - name: Precision
-      type: precision
+      name: Accuracy
+    - type: precision
       value: 0.8801652892561983
-    - name: Recall
-      type: recall
+      name: Precision
+    - type: recall
       value: 0.8783505154639175
-    - name: F1
-      type: f1
+      name: Recall
+    - type: f1
       value: 0.8792569659442725
+      name: F1
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}