Upload tokenizer

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6cccb97cd670a2be86164ecd1675945060cf22e9a95df034681e52bd1928aa
-size 802691
+oid sha256:640115634b6b559a15bce8fad333e3b0eb835fce07a253d78f22961c0a5c7864
+size 802696

tokenizer.json

@@ -13,8 +13,8 @@
       "special": true
     },
     {
-      "id": 2,
-      "content": "</s>",
+      "id": 1,
+      "content": "<pad>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -22,8 +22,8 @@
       "special": true
     },
     {
-      "id": 3,
-      "content": "<unk>",
+      "id": 2,
+      "content": "</s>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -31,8 +31,8 @@
       "special": true
     },
     {
-      "id": 4,
-      "content": "<pad>",
+      "id": 3,
+      "content": "<unk>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -162,10 +162,6 @@
         "<unk>",
         0.0
       ],
-      [
-        "<pad>",
-        0.0
-      ],
       [
         "▁the",
         -2.9545793533325195
@@ -128149,6 +128145,10 @@
       [
         "Aquila",
         -13.928366661071777
+      ],
+      [
+        "9.6",
+        -13.928522109985352
       ]
     ],
     "byte_fallback": false

tokenizer_config.json

@@ -9,24 +9,24 @@
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "<pad>",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,