Upload folder using huggingface_hub

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": [
@@ -129,7 +119,7 @@
   "model": {
     "type": "BPE",
     "dropout": null,
-    "unk_token": "<unk>",
+    "unk_token": null,
     "continuing_subword_prefix": null,
     "end_of_word_suffix": null,
     "fuse_unk": true,

tokenizer_config.json

@@ -1,38 +1,11 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
   "add_prefix_space": null,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
+  "backend": "tokenizers",
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "extra_special_tokens": {},
-  "legacy": false,
+  "is_local": false,
+  "local_files_only": false,
   "model_max_length": 2048,
   "pad_token": "</s>",
   "padding_side": "right",