Upload tokenizer

special_tokens_map.json

@@ -1,5 +1,23 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "unk_token": "<unk>"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -31,23 +31,13 @@
       "special": true
     }
   ],
-  "normalizer": {
-    "type": "Sequence",
-    "normalizers": [
-      {
-        "type": "Prepend",
-        "prepend": "▁"
-      },
-      {
-        "type": "Replace",
-        "pattern": {
-          "String": " "
-        },
-        "content": "▁"
-      }
-    ]
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Metaspace",
+    "replacement": "▁",
+    "prepend_scheme": "first",
+    "split": false
   },
-  "pre_tokenizer": null,
   "post_processor": {
     "type": "TemplateProcessing",
     "single": [
@@ -134,6 +124,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -31,7 +32,7 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
+  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},