Upload tokenizer

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "bos_token": {
-    "content": "[BOS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "[EOS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenization.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77e8519d158dc272f59cc782244f3cde7a8fc01f59d4bd67b3812209837ad6f
-size 489008
+oid sha256:8e379c61626c16c090dac9fa2da11c075dc6ff840e5e1c82cc19720392d7a282
+size 488981

tokenizer.json

@@ -5,7 +5,7 @@
   "added_tokens": [
     {
       "id": 0,
-      "content": "[PAD]",
+      "content": "<pad>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -14,7 +14,7 @@
     },
     {
       "id": 1,
-      "content": "[UNK]",
+      "content": "<unk>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -23,7 +23,7 @@
     },
     {
       "id": 2,
-      "content": "[BOS]",
+      "content": "<s>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -32,7 +32,7 @@
     },
     {
       "id": 3,
-      "content": "[EOS]",
+      "content": "</s>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -41,30 +41,12 @@
     },
     {
       "id": 4,
-      "content": "[CLS]",
+      "content": "<mask>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
       "normalized": false,
-      "special": true
-    },
-    {
-      "id": 5,
-      "content": "[SEP]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 6,
-      "content": "[MASK]",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
+      "special": false
     }
   ],
   "normalizer": {
@@ -106,31 +88,23 @@
     "unk_id": 1,
     "vocab": [
       [
-        "[PAD]",
-        0.0
-      ],
-      [
-        "[UNK]",
-        0.0
-      ],
-      [
-        "[BOS]",
+        "<pad>",
         0.0
       ],
       [
-        "[EOS]",
+        "<unk>",
         0.0
       ],
       [
-        "[CLS]",
+        "<s>",
         0.0
       ],
       [
-        "[SEP]",
+        "</s>",
         0.0
       ],
       [
-        "[MASK]",
+        "<mask>",
         0.0
       ],
       [
@@ -60365,6 +60339,14 @@
         "imillar",
         -12.87510871887207
       ],
+      [
+        ".62%",
+        -12.876296043395996
+      ],
+      [
+        "▁Excel",
+        -12.88099193572998
+      ],
       [
         "Ƴ",
         -14.629597663879396

tokenizer_config.json

@@ -4,7 +4,7 @@
   "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -12,7 +12,7 @@
       "special": true
     },
     "1": {
-      "content": "[UNK]",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -20,7 +20,7 @@
       "special": true
     },
     "2": {
-      "content": "[BOS]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -28,7 +28,7 @@
       "special": true
     },
     "3": {
-      "content": "[EOS]",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -36,48 +36,28 @@
       "special": true
     },
     "4": {
-      "content": "[CLS]",
+      "content": "<mask>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": "[SEP]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
+      "special": false
     }
   },
-  "bos_token": "[BOS]",
+  "bos_token": "<s>",
   "bos_token_id": 2,
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "cls_token_id": 4,
-  "eos_token": "[EOS]",
+  "eos_token": "</s>",
   "eos_token_id": 3,
   "legacy": true,
-  "mask_token": "[MASK]",
-  "mask_token_id": 6,
+  "mask_token": "<mask>",
+  "mask_token_id": 4,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
   "pad_token_id": 0,
-  "sep_token": "[SEP]",
-  "sep_token_id": 5,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "tokenizer_class": "HfTokenizerFromConfig",
-  "unk_token": "[UNK]",
+  "tokenizer_class": "HfSentencePieceTokenizer",
+  "unk_token": "<unk>",
   "unk_token_id": 1
 }