Upload tokenizer

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: Lakoc/DeCRED_small_cv
 tags:
 - generated_from_trainer
+base_model: Lakoc/DeCRED_small_cv
 datasets:
 - fleurs
 model-index:

special_tokens_map.json

@@ -1,34 +1,41 @@
 {
   "bos_token": {
-    "content": "<s>",
+    "content": "([bos])",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
-    "content": "</s>",
+    "content": "([eos])",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "mask_token": {
-    "content": "<mask>",
+    "content": "([mask])",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<pad>",
+    "content": "([pad])",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "▁",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "unk_token": {
-    "content": "<unk>",
+    "content": "([unk])",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "([bos])",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "</s>",
+      "content": "([eos])",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "<unk>",
+      "content": "([unk])",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": true
     },
     "3": {
-      "content": "<pad>",
+      "content": "([pad])",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -33,7 +33,15 @@
       "special": true
     },
     "4": {
-      "content": "<mask>",
+      "content": "([mask])",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,12 +49,13 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "([bos])",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "eos_token": "([eos])",
+  "mask_token": "([mask])",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
+  "pad_token": "([pad])",
+  "sep_token": "▁",
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "unk_token": "<unk>"
+  "unk_token": "([unk])"
 }